{
  "title": "generate.directory",
  "verifiedAt": "2026-10-19",
  "method": "Official API and developer documentation reviewed; paid generation endpoints were not called.",
  "categories": [
    {
      "name": "Image Generation",
      "key": "image-generation",
      "color": "#15AD70",
      "description": "Text, references & custom image models",
      "count": 13
    },
    {
      "name": "Video Generation",
      "key": "video-generation",
      "color": "#7193ED",
      "description": "Text-to-video & image-to-video APIs",
      "count": 9
    },
    {
      "name": "Speech Generation",
      "key": "speech-generation",
      "color": "#EB546F",
      "description": "Text-to-speech & streaming audio",
      "count": 15
    },
    {
      "name": "Multimodal APIs",
      "key": "multimodal-apis",
      "color": "#F78D2C",
      "description": "Image, video & voice in one platform",
      "count": 5
    },
    {
      "name": "Image Editing",
      "key": "image-editing",
      "color": "#82D25D",
      "description": "Backgrounds, retouching & transformations",
      "count": 4
    },
    {
      "name": "Avatars & Lip Sync",
      "key": "avatars-lip-sync",
      "color": "#A3B4F4",
      "description": "Talking avatars & synchronized video",
      "count": 9
    },
    {
      "name": "Voice Cloning",
      "key": "voice-cloning",
      "color": "#F9C3D6",
      "description": "Custom voices & speech synthesis",
      "count": 3
    },
    {
      "name": "Inference Platforms",
      "key": "inference-platforms",
      "color": "#E4E986",
      "description": "Hosted models & generation infrastructure",
      "count": 13
    }
  ],
  "providers": [
    {
      "name": "Black Forest Labs",
      "url": "https://api.bfl.ai/docs",
      "category": "Image Generation",
      "description": "FLUX image generation and editing APIs, including inpainting and image expansion.",
      "tags": [
        "image",
        "editing",
        "inpainting"
      ],
      "sourceUrl": "https://api.bfl.ai/docs",
      "evidence": "Official API reference documents FLUX generation, editing, fill and expand endpoints.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 267120124,
      "logo": "logos/267120124.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/bfl.svg"
    },
    {
      "name": "Stability AI",
      "url": "https://platform.stability.ai/docs/getting-started/stable-image",
      "category": "Image Generation",
      "description": "Stable Image APIs for text-to-image generation and image processing.",
      "tags": [
        "image",
        "text-to-image"
      ],
      "sourceUrl": "https://platform.stability.ai/docs/getting-started/stable-image",
      "evidence": "Official developer platform documents Stable Image services and the REST v2beta API.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 53914397,
      "logo": "logos/53914397.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/stability.svg"
    },
    {
      "name": "Ideogram",
      "url": "https://developer.ideogram.ai/ideogram-api/api-overview",
      "category": "Image Generation",
      "description": "Image generation and targeted editing through a documented developer API.",
      "tags": [
        "image",
        "editing",
        "text-to-image"
      ],
      "sourceUrl": "https://developer.ideogram.ai/ideogram-api/api-overview",
      "evidence": "Official overview documents image generation endpoints and precise image editing.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 107858111,
      "logo": "logos/107858111.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/ideogram.svg"
    },
    {
      "name": "Recraft",
      "url": "https://www.recraft.ai/api",
      "category": "Image Generation",
      "description": "API for generating and editing raster images and vector graphics.",
      "tags": [
        "image",
        "editing",
        "vector"
      ],
      "sourceUrl": "https://www.recraft.ai/api",
      "evidence": "Official API landing page offers image and vector generation and editing with linked documentation.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 165897491,
      "logo": "logos/165897491.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/recraft.svg"
    },
    {
      "name": "Leonardo.Ai",
      "url": "https://docs.leonardo.ai/docs/getting-started",
      "category": "Image Generation",
      "description": "Developer API for generating images from text prompts and model settings.",
      "tags": [
        "image",
        "text-to-image"
      ],
      "sourceUrl": "https://docs.leonardo.ai/docs/getting-started",
      "evidence": "Quickstart shows API key creation and POST /api/rest/v1/generations returning a generation ID.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 12781666,
      "logo": "logos/12781666.svg",
      "logoMode": "mask",
      "logoSource": "https://t2.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=http://leonardo.ai&size=128"
    },
    {
      "name": "Bria",
      "url": "https://docs.bria.ai/",
      "category": "Image Generation",
      "description": "Image generation API accepting text prompts, reference images and structured prompts.",
      "tags": [
        "image",
        "text-to-image",
        "image-to-image"
      ],
      "sourceUrl": "https://docs.bria.ai/image-generation/generation",
      "evidence": "Official generation documentation describes text, reference-image and structured-prompt generation.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 186743700,
      "logo": "logos/186743700.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/briaai.svg"
    },
    {
      "name": "Photoroom",
      "url": "https://www.photoroom.com/api",
      "category": "Image Editing",
      "description": "Photo editing API for background removal, generated backgrounds, relighting and image expansion.",
      "tags": [
        "image",
        "editing",
        "background-removal",
        "upscaling"
      ],
      "sourceUrl": "https://docs.photoroom.com/",
      "evidence": "Official docs list image editing and background removal APIs with AI backgrounds, relighting and expand.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 212643730,
      "logo": "logos/212643730.svg",
      "logoMode": "mask",
      "logoSource": "https://www.photoroom.com/favicons/safari-pinned-tab.svg"
    },
    {
      "name": "remove.bg",
      "url": "https://www.remove.bg/api",
      "category": "Image Editing",
      "description": "Background removal API accepting uploaded images or image URLs.",
      "tags": [
        "image",
        "editing",
        "background-removal"
      ],
      "sourceUrl": "https://www.remove.bg/api",
      "evidence": "Official documentation provides POST /v1.0/removebg; migration to Leonardo.Ai is announced for December 1, 2026.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 47156085,
      "logo": "logos/47156085.svg",
      "logoMode": "mask",
      "logoSource": "https://www.remove.bg/apple-touch-icon.png?v=fc0bfce6e1310f1539afec9729716721"
    },
    {
      "name": "getimg.ai",
      "url": "https://getimg.ai/developers/ai-image-generator-api",
      "category": "Image Generation",
      "description": "Text-to-image API exposing multiple image models through a shared request format.",
      "tags": [
        "image",
        "text-to-image",
        "multi-model"
      ],
      "sourceUrl": "https://getimg.ai/developers/ai-image-generator-api",
      "evidence": "Official developer page provides SDK examples and a shared image-generation endpoint and request shape.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 63104479,
      "logo": "logos/63104479.svg",
      "logoMode": "mask",
      "logoSource": "https://getimg.ai/icons/apple-touch-icon.png?v=20260703"
    },
    {
      "name": "Segmind",
      "url": "https://docs.segmind.com/docs/get-started",
      "category": "Image Generation",
      "description": "Hosted model APIs for image generation with examples for common programming languages.",
      "tags": [
        "image",
        "text-to-image",
        "multi-model"
      ],
      "sourceUrl": "https://docs.segmind.com/docs/get-started",
      "evidence": "Official quickstart demonstrates an API-key-authenticated image-generation request to fast-flux-schnell.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 131844537,
      "logo": "logos/131844537.svg",
      "logoMode": "mask",
      "logoSource": "https://www.segmind.com/favicon.svg"
    },
    {
      "name": "Scenario",
      "url": "https://docs.scenario.com/get-started/documentation/key-capabilities-at-a-glance",
      "category": "Image Generation",
      "description": "Image generation API with reference images and custom-trained models.",
      "tags": [
        "image",
        "text-to-image",
        "image-to-image",
        "fine-tuning"
      ],
      "sourceUrl": "https://docs.scenario.com/get-started/documentation/key-capabilities-at-a-glance",
      "evidence": "Official docs describe text-to-image, image-to-image and custom LoRA generation using its REST API.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 249720641,
      "logo": "logos/249720641.svg",
      "logoMode": "mask",
      "logoSource": "https://www.scenario.com/apple-touch-icon.png"
    },
    {
      "name": "Runware",
      "url": "https://runware.ai/docs",
      "category": "Image Generation",
      "description": "Unified model API for image generation, image editing and media processing.",
      "tags": [
        "image",
        "editing",
        "multi-model"
      ],
      "sourceUrl": "https://runware.ai/docs",
      "evidence": "Official documentation lists text-to-image, instruction-based editing, inpainting and outpainting capabilities.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 239537545,
      "logo": "logos/239537545.svg",
      "logoMode": "mask",
      "logoSource": "https://website.runware.ai/favicon.svg"
    },
    {
      "name": "LightX",
      "url": "https://www.lightxeditor.com/api/",
      "category": "Image Editing",
      "description": "Photo API for background removal, image generation, cleanup and product photoshoots.",
      "tags": [
        "image",
        "editing",
        "background-removal",
        "text-to-image"
      ],
      "sourceUrl": "https://www.lightxeditor.com/api/",
      "evidence": "Official API page lists text-to-image, cleanup and product photoshoot APIs and provides authenticated sample requests.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 36177827,
      "logo": "logos/36177827.svg",
      "logoMode": "mask",
      "logoSource": "https://www.lightxeditor.com/favicon.ico"
    },
    {
      "name": "Picsart",
      "url": "https://picsart.com/api-platform/docs",
      "category": "Image Editing",
      "description": "Creative APIs for prompt-based image editing, background removal and generative media.",
      "tags": [
        "image",
        "editing",
        "background-removal"
      ],
      "sourceUrl": "https://docs.picsart.io/reference/genai-image-edit",
      "evidence": "Official reference documents POST /v1/painting/edit for asynchronous prompt-based image transformations.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 245726214,
      "logo": "logos/245726214.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.simpleicons.org/picsart"
    },
    {
      "name": "Astria",
      "url": "https://docs.astria.ai/docs/api/overview/",
      "category": "Image Generation",
      "description": "Fine-tuning and image generation API organized around trained models and prompts.",
      "tags": [
        "image",
        "fine-tuning",
        "custom-models"
      ],
      "sourceUrl": "https://docs.astria.ai/docs/api/overview/",
      "evidence": "Official documentation describes bearer-authenticated REST tune and prompt resources and generated images.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 96179278,
      "logo": "logos/96179278.svg",
      "logoMode": "mask",
      "logoSource": "https://a.astria.ai/assets/favicon/favicon-56fc2dd378a3ed665741439d9bff745a2d2a9c6c8ef308c93bc2752f5bd4cd4c.ico"
    },
    {
      "name": "DeepAI",
      "url": "https://api.deepai.org/docs",
      "category": "Image Generation",
      "description": "HTTP APIs for text-to-image generation, photo editing, upscaling and background removal.",
      "tags": [
        "image",
        "editing",
        "text-to-image",
        "upscaling"
      ],
      "sourceUrl": "https://api.deepai.org/docs",
      "evidence": "Official docs list image APIs and show POST /api/text2img with an API key and text prompt.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 63629107,
      "logo": "logos/63629107.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/deepai.svg"
    },
    {
      "name": "Magnific (formerly Freepik)",
      "url": "https://docs.magnific.com/introduction",
      "category": "Image Generation",
      "description": "APIs for image generation, image editing, upscaling, relighting and icon generation.",
      "tags": [
        "image",
        "editing",
        "text-to-image",
        "upscaling"
      ],
      "sourceUrl": "https://docs.magnific.com/introduction",
      "evidence": "Freepik docs redirect to Magnific; current official documentation lists image generation and editing APIs.",
      "checkedAt": "2026-10-19",
      "logoUrl": null,
      "id": 131685705,
      "logo": "logos/131685705.svg",
      "logoMode": "mask",
      "logoSource": "https://media.magnific.com/magnific-favicons/favicon.ico"
    },
    {
      "name": "Runway",
      "url": "https://docs.dev.runwayml.com/",
      "category": "Video Generation",
      "description": "Generate video from text, images, and existing footage through Runway’s developer API.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://docs.dev.runwayml.com/api/",
      "evidence": "Official API reference lists text-to-video, image-to-video, and video-to-video generation endpoints.",
      "logoUrl": "https://runway.com/icon.png?icon.35ps9bmugbe1e.png",
      "checkedAt": "2026-10-19",
      "id": 182876546,
      "logo": "logos/182876546.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/runway.svg"
    },
    {
      "name": "Luma",
      "url": "https://docs.agents.lumalabs.ai/",
      "category": "Video Generation",
      "description": "Generate and edit videos with Luma’s Ray models through an asynchronous REST API.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://docs.agents.lumalabs.ai/",
      "evidence": "Official quickstart documents authenticated video generation and image start/end frames through the Luma Agents API.",
      "logoUrl": "https://lumalabs.ai/favicons/favicon-black.ico",
      "checkedAt": "2026-10-19",
      "id": 87034306,
      "logo": "logos/87034306.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/luma.svg"
    },
    {
      "name": "Kling AI",
      "url": "https://kling.ai/",
      "category": "Video Generation",
      "description": "Kuaishou’s video generation platform with a developer API for prompt-driven video creation.",
      "tags": [
        "video",
        "text-to-video"
      ],
      "sourceUrl": "https://kling.ai/document-api/api/video/3-0-omni/text-to-video/legacy",
      "evidence": "Official Kling API documentation exposes a text-to-video request at api-singapore.klingai.com/v1/videos/text2video.",
      "logoUrl": "https://s16-kling.klingai.com/kos/s101/nlav112918/kling-homepage-aio/favicon.ico",
      "checkedAt": "2026-10-19",
      "id": 81303443,
      "logo": "logos/81303443.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/kling.svg"
    },
    {
      "name": "MiniMax",
      "url": "https://platform.minimax.io/docs/guides/video-generation",
      "category": "Video Generation",
      "description": "Create video from text, images, and media references using MiniMax’s video generation API.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://platform.minimax.io/docs/guides/video-generation",
      "evidence": "Official developer guide documents MiniMax H3 API access and text-to-video, image-to-video, and reference generation.",
      "logoUrl": "https://www.minimax.io/favicon.ico",
      "checkedAt": "2026-10-19",
      "id": 236263358,
      "logo": "logos/236263358.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/minimax.svg"
    },
    {
      "name": "LTX",
      "url": "https://docs.ltx.video/",
      "category": "Video Generation",
      "description": "Lightricks’ video API generates synchronized video and audio from text, image, or audio inputs.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://docs.ltx.video/",
      "evidence": "Official API documentation provides developer-console key access and synchronous and asynchronous generation APIs.",
      "logoUrl": null,
      "checkedAt": "2026-10-19",
      "id": 23161428,
      "logo": "logos/23161428.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/lightricks.svg"
    },
    {
      "name": "Pika",
      "url": "https://dev.pika.art/",
      "category": "Video Generation",
      "description": "Access Pika video generation and editing models through Pika’s official developer API.",
      "tags": [
        "video",
        "text-to-video"
      ],
      "sourceUrl": "https://dev.pika.art/models/pika/pika-2.5/text-to-video/playground",
      "evidence": "Official Pika API platform lists a Pika 2.5 text-to-video model playground; Pika support directs developers to dev.pika.art.",
      "logoUrl": "https://dev.pika.art/favicon.ico?favicon.2ypdzzwafbco6.ico",
      "checkedAt": "2026-10-19",
      "id": 93857654,
      "logo": "logos/93857654.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/pika.svg"
    },
    {
      "name": "PixVerse",
      "url": "https://platform.pixverse.ai/",
      "category": "Video Generation",
      "description": "Generate video from text or images, apply effects, and synchronize speech using PixVerse’s API.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video",
        "lip-sync"
      ],
      "sourceUrl": "https://docs.platform.pixverse.ai/pixverse-api-llm-txt-2109771m0",
      "evidence": "Official API guide documents API-key authentication, text/image generation endpoints, and speech lip-sync generation.",
      "logoUrl": "https://cdn.pixverse.ai/media/pixverse/favicon.svg",
      "checkedAt": "2026-10-19",
      "id": 95310207,
      "logo": "logos/95310207.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/pixverse.svg"
    },
    {
      "name": "Vidu",
      "url": "https://platform.vidu.com/",
      "category": "Video Generation",
      "description": "Generate video from text, images, and references through Vidu’s authenticated developer API.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://platform.vidu.com/docs/api-reference/video-models/vidu-q1/image-to-video",
      "evidence": "Official API reference documents image-to-video generation and links text-to-video, start/end, and reference-to-video modes.",
      "logoUrl": "https://www.vidu.com/logo.svg",
      "checkedAt": "2026-10-19",
      "id": 267844998,
      "logo": "logos/267844998.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/vidu.svg"
    },
    {
      "name": "Alibaba Cloud Wan",
      "url": "https://www.alibabacloud.com/help/en/model-studio/use-video-generation/",
      "category": "Video Generation",
      "description": "Generate videos from text, images, and references using Wan models on Alibaba Cloud Model Studio.",
      "tags": [
        "video",
        "text-to-video",
        "image-to-video"
      ],
      "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/use-video-generation/",
      "evidence": "Official Model Studio documentation links Wan text-to-video and image-to-video API references and describes DashScope access.",
      "logoUrl": "https://img.alicdn.com/tfs/TB1ugg7M9zqK1RjSZPxXXc4tVXa-32-32.png",
      "checkedAt": "2026-10-19",
      "id": 219524300,
      "logo": "logos/219524300.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/alibabacloud.svg"
    },
    {
      "name": "HeyGen",
      "url": "https://developers.heygen.com/",
      "category": "Avatars & Lip Sync",
      "description": "Create avatar videos, digital twins, translations, and lip-synced media through HeyGen’s developer APIs.",
      "tags": [
        "video",
        "avatar",
        "lip-sync"
      ],
      "sourceUrl": "https://developers.heygen.com/",
      "evidence": "Official developer platform offers API-key access and documents avatar video generation, digital twins, and lip-sync APIs.",
      "logoUrl": "https://www.heygen.com/favicon.ico?favicon.2m321y0geyyfh.ico",
      "checkedAt": "2026-10-19",
      "id": 100654220,
      "logo": "logos/100654220.svg",
      "logoMode": "mask",
      "logoSource": "https://www.heygen.com/favicon.ico?favicon.2m321y0geyyfh.ico"
    },
    {
      "name": "D-ID",
      "url": "https://docs.d-id.com/",
      "category": "Avatars & Lip Sync",
      "description": "Create talking avatars and digital presenters, and translate videos using D-ID’s APIs.",
      "tags": [
        "video",
        "avatar",
        "lip-sync"
      ],
      "sourceUrl": "https://docs.d-id.com/docs/quickstart",
      "evidence": "Official quickstart describes video APIs for talking avatars, translated videos, and custom digital presenters.",
      "logoUrl": "https://www.d-id.com/wp-content/uploads/2024/10/D-ID-logo-350x350-1-150x150.png",
      "checkedAt": "2026-10-19",
      "id": 79239253,
      "logo": "logos/79239253.svg",
      "logoMode": "mask",
      "logoSource": "https://t3.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=http://d-id.com&size=128"
    },
    {
      "name": "Tavus",
      "url": "https://www.tavus.io/",
      "category": "Avatars & Lip Sync",
      "description": "Generate talking-head videos from scripts using Tavus digital replicas and a developer API.",
      "tags": [
        "video",
        "avatar",
        "text-to-video"
      ],
      "sourceUrl": "https://www.tavus.io/blog/how-to-do-text-to-video-for-ai-replicas",
      "evidence": "Official tutorial documents API-key authentication and POST tavusapi.com/v2/videos with a replica ID and script.",
      "logoUrl": "https://cdn.prod.website-files.com/68c8e57d6e512b9573db146f/68c8e57e6e512b9573db1acd_Favicon%20Dark.ico",
      "checkedAt": "2026-10-19",
      "id": 182636651,
      "logo": "logos/182636651.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/68c8e57d6e512b9573db146f/68c8e57e6e512b9573db1acd_Favicon%20Dark.ico"
    },
    {
      "name": "Synthesia",
      "url": "https://www.synthesia.io/api",
      "category": "Avatars & Lip Sync",
      "description": "Generate scripted avatar videos, dubbing, and translations through Synthesia’s APIs.",
      "tags": [
        "video",
        "avatar",
        "lip-sync"
      ],
      "sourceUrl": "https://docs.synthesia.io/reference/introduction",
      "evidence": "Official API introduction distinguishes live lip-synced avatars from the asynchronous Video API for finished avatar videos.",
      "logoUrl": "https://cdn.prod.website-files.com/65e89895c5a4b8d764c0d710/664f0f482fa5a4d527d892bc_Favicon-Web-Security%201.png",
      "checkedAt": "2026-10-19",
      "id": 262592487,
      "logo": "logos/262592487.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/65e89895c5a4b8d764c0d710/664f0f482fa5a4d527d892bc_Favicon-Web-Security%201.png"
    },
    {
      "name": "AKOOL",
      "url": "https://akool.com/openapi",
      "category": "Avatars & Lip Sync",
      "description": "Add talking avatars, streaming avatars, and video translation to applications using AKOOL’s API.",
      "tags": [
        "video",
        "avatar"
      ],
      "sourceUrl": "https://akool.com/openapi",
      "evidence": "Official Open API page provides developer credentials and API documentation for avatar and video tools.",
      "logoUrl": "https://akool.com/favicon.ico?favicon.3h-fx0a0eudfo.ico",
      "checkedAt": "2026-10-19",
      "id": 213012724,
      "logo": "logos/213012724.svg",
      "logoMode": "mask",
      "logoSource": "https://akool.com/favicon.ico?favicon.3h-fx0a0eudfo.ico"
    },
    {
      "name": "Hedra",
      "url": "https://www.hedra.com/develop",
      "category": "Avatars & Lip Sync",
      "description": "Generate talking and singing character videos with Hedra’s avatar models through its developer API.",
      "tags": [
        "video",
        "avatar",
        "lip-sync"
      ],
      "sourceUrl": "https://www.hedra.com/develop/models/video",
      "evidence": "Official developer catalog includes Hedra Avatar and Character 3 audio-to-video models for talking and singing videos.",
      "logoUrl": "https://www.hedra.com/favicon.ico",
      "checkedAt": "2026-10-19",
      "id": 17530623,
      "logo": "logos/17530623.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/hedra.svg"
    },
    {
      "name": "Sync",
      "url": "https://sync.so/",
      "category": "Avatars & Lip Sync",
      "description": "Synchronize lip movements in video or images to supplied audio or text through Sync’s REST API.",
      "tags": [
        "video",
        "lip-sync"
      ],
      "sourceUrl": "https://sync.so/docs/de/api-reference/api-overview",
      "evidence": "Official API overview documents API-key authentication and POST /v2/generate for lip-synced media creation.",
      "logoUrl": "https://framerusercontent.com/images/0Xql4PYHN997ZZPpnWpWkPU9uI.png",
      "checkedAt": "2026-10-19",
      "id": 123500015,
      "logo": "logos/123500015.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/sync.svg"
    },
    {
      "name": "Colossyan",
      "url": "https://www.colossyan.com/features/api/",
      "category": "Avatars & Lip Sync",
      "description": "Generate personalized avatar videos and create custom avatars using Colossyan’s REST API.",
      "tags": [
        "video",
        "avatar"
      ],
      "sourceUrl": "https://docs.colossyan.com/",
      "evidence": "Official documentation describes a JSON REST API for programmable video creation, avatars, and template rendering.",
      "logoUrl": "https://lp-assets.colossyan.com/website-images/images/images/favicon.png",
      "checkedAt": "2026-10-19",
      "id": 235272663,
      "logo": "logos/235272663.svg",
      "logoMode": "mask",
      "logoSource": "https://lp-assets.colossyan.com/website-images/images/images/favicon.png"
    },
    {
      "name": "Elai",
      "url": "https://elai.io/",
      "category": "Avatars & Lip Sync",
      "description": "Generate and personalize digital-presenter videos programmatically through Elai’s video APIs.",
      "tags": [
        "video",
        "avatar",
        "text-to-video"
      ],
      "sourceUrl": "https://elai.readme.io/reference/getting-started-with-your-api",
      "evidence": "Official API guide documents admin-created bearer tokens, video rendering, and Story API generation from text and other sources.",
      "logoUrl": null,
      "checkedAt": "2026-10-19",
      "id": 60707317,
      "logo": "logos/60707317.svg",
      "logoMode": "mask",
      "logoSource": "https://t3.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=http://elai.io&size=128"
    },
    {
      "name": "ElevenLabs",
      "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech",
      "category": "Speech Generation",
      "description": "Generate expressive speech from text with multilingual voices and real-time audio streaming.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech",
      "evidence": "Official TTS docs describe an API that converts text to audio and streams real-time speech across languages.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://elevenlabs.io/docs/api/fern-docs/favicon.ico",
      "id": 243612494,
      "logo": "logos/243612494.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/elevenlabs.svg"
    },
    {
      "name": "Cartesia",
      "url": "https://docs.cartesia.ai/get-started/overview",
      "category": "Speech Generation",
      "description": "Sonic speech models provide streaming text-to-speech and voice cloning for conversational applications.",
      "tags": [
        "speech",
        "streaming",
        "voice-cloning"
      ],
      "sourceUrl": "https://docs.cartesia.ai/get-started/overview",
      "evidence": "Official docs expose Sonic text-to-speech models that stream generated audio and support voice cloning.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.cartesia.ai/mintlify-assets/_mintlify/favicons/cartesia-2650f86a/BVkNMOvjsiwM8WQI/_generated/favicon/android-chrome-192x192.png",
      "id": 160316064,
      "logo": "logos/160316064.svg",
      "logoMode": "mask",
      "logoSource": "https://www.cartesia.ai/favicon.svg"
    },
    {
      "name": "Deepgram",
      "url": "https://developers.deepgram.com/home/",
      "category": "Speech Generation",
      "description": "Generate speech with Aura voices through REST and continuous text streaming APIs.",
      "tags": [
        "speech",
        "streaming"
      ],
      "sourceUrl": "https://developers.deepgram.com/home/",
      "evidence": "Developer docs list Text to Speech APIs for a single text request and a continuous text stream.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://developers.deepgram.com/api/fern-docs/favicon.ico",
      "id": 260590040,
      "logo": "logos/260590040.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.simpleicons.org/deepgram"
    },
    {
      "name": "Murf",
      "url": "https://murf.ai/api/docs/api-reference/text-to-speech/generate",
      "category": "Speech Generation",
      "description": "Text-to-speech APIs offer voice selection, pronunciation controls, multilingual output, and streaming.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://murf.ai/api/docs/api-reference/text-to-speech/generate",
      "evidence": "Synthesize Speech documents POST /v1/speech/generate; official streaming docs describe HTTP and WebSocket synthesis.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://murf.ai/api/docs/api/fern-docs/favicon.ico",
      "id": 135339375,
      "logo": "logos/135339375.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/66b3765153a8a0c399c70981/670cb2af23deffa700aa8a09_favicon.ico"
    },
    {
      "name": "WellSaid",
      "url": "https://docs.wellsaidlabs.com/reference/getting-started-with-your-api",
      "category": "Speech Generation",
      "description": "Synthesize voiceovers through a text-to-speech API with streaming audio and selectable voice models.",
      "tags": [
        "speech",
        "streaming"
      ],
      "sourceUrl": "https://docs.wellsaidlabs.com/reference/getting-started-with-your-api",
      "evidence": "Official quickstart generates MP3 audio using POST https://api.wellsaidlabs.com/v1/tts/stream with an API key.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://files.readme.io/8248cd9dc8b70f17f9ba1994287cf6bacf7c8ede7aa447e3bf09b276f4ea6285-small-Logomark_Thumbnail_WSL_Team.png",
      "id": 240509932,
      "logo": "logos/240509932.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/673384264721b089c7e053a7/6735be4cdc0c4b05e9e4a393_favicon-32%20(1).png"
    },
    {
      "name": "Speechify",
      "url": "https://docs.speechify.ai/",
      "category": "Speech Generation",
      "description": "Simba models generate and stream speech with SSML controls, multilingual voices, and custom voice cloning.",
      "tags": [
        "speech",
        "streaming",
        "voice-cloning",
        "multilingual"
      ],
      "sourceUrl": "https://docs.speechify.ai/",
      "evidence": "Official Build docs show POST /v1/audio/speech and document streaming, voice cloning, and multilingual Simba models.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.speechify.ai/api/fern-docs/favicon.ico",
      "id": 120428202,
      "logo": "logos/120428202.svg",
      "logoMode": "mask",
      "logoSource": "https://speechify.com/favicon.ico?favicon.3a2yv0cbavf6m.ico"
    },
    {
      "name": "Rime",
      "url": "https://docs.rime.ai/",
      "category": "Speech Generation",
      "description": "Generate speech through HTTP and WebSocket APIs with voice selection and delivery controls.",
      "tags": [
        "speech",
        "streaming"
      ],
      "sourceUrl": "https://docs.rime.ai/",
      "evidence": "Official docs show authenticated POST https://users.rime.ai/v1/rime-tts and describe HTTP and WebSocket streaming.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.rime.ai/mintlify-assets/_mintlify/favicons/rimelabs/yDOD7F9UdOtEHeIJ/_generated/favicon/android-chrome-192x192.png",
      "id": 184890081,
      "logo": "logos/184890081.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/6a4d70b04f64b0fe572eff71/6a554ed164ebbebdec8f30d9_rime_LinkedIn_profile.png"
    },
    {
      "name": "Hume",
      "url": "https://dev.hume.ai/voice/reference/text-to-speech-tts/synthesize-json",
      "category": "Speech Generation",
      "description": "Octave generates expressive speech with natural-language delivery prompts and controls for pace and silence.",
      "tags": [
        "speech"
      ],
      "sourceUrl": "https://dev.hume.ai/voice/reference/text-to-speech-tts/synthesize-json",
      "evidence": "Official TTS reference documents POST /v0/tts with input text, voice selection, description, speed, and trailing silence.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://dev.hume.ai/api/fern-docs/favicon.ico",
      "id": 100988729,
      "logo": "logos/100988729.svg",
      "logoMode": "mask",
      "logoSource": "https://www.hume.ai/favicon.ico?favicon.bd1999a1.ico"
    },
    {
      "name": "Fish Audio",
      "url": "https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech",
      "category": "Voice Cloning",
      "description": "Generate speech and multi-speaker dialogue using voice models or reference audio for zero-shot cloning.",
      "tags": [
        "speech",
        "voice-cloning"
      ],
      "sourceUrl": "https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech",
      "evidence": "Official POST /v1/tts reference supports reference audio for zero-shot cloning and multiple speaker voice IDs for dialogue.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.fish.audio/mintlify-assets/_mintlify/favicons/hanabiaiinc/rHJNuwD9FcQhvMwX/_generated/favicon/android-chrome-192x192.png",
      "id": 192312651,
      "logo": "logos/192312651.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/fishaudio.svg"
    },
    {
      "name": "Smallest AI",
      "url": "https://docs.smallest.ai/overview/introduction",
      "category": "Voice Cloning",
      "description": "Lightning models synthesize and stream speech, with voice cloning from short reference recordings.",
      "tags": [
        "speech",
        "streaming",
        "voice-cloning",
        "multilingual"
      ],
      "sourceUrl": "https://docs.smallest.ai/overview/introduction",
      "evidence": "Official docs expose TTS over HTTP, SSE, and WebSocket plus voice cloning; synthesis reference documents language selection.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.smallest.ai/api/fern-docs/favicon.ico",
      "id": 247376965,
      "logo": "logos/247376965.svg",
      "logoMode": "mask",
      "logoSource": "https://framerusercontent.com/images/8aGg1mfHwnBJJYiECyUmneAyRVA.png"
    },
    {
      "name": "Inworld",
      "url": "https://docs.inworld.ai/tts/tts",
      "category": "Speech Generation",
      "description": "Generate multilingual speech with streaming, natural-language delivery steering, and instant voice cloning.",
      "tags": [
        "speech",
        "streaming",
        "voice-cloning",
        "multilingual"
      ],
      "sourceUrl": "https://docs.inworld.ai/tts/tts",
      "evidence": "Official TTS overview provides SDK generation examples and links streaming, supported languages, and instant voice cloning.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.inworld.ai/logo/light.svg",
      "id": 236506874,
      "logo": "logos/236506874.svg",
      "logoMode": "mask",
      "logoSource": "https://inworld.ai/favicon.ico?favicon.22-v1jeb_rtrm.ico"
    },
    {
      "name": "ReadSpeaker",
      "url": "https://www.readspeaker.com/products/speechcloud-api/",
      "category": "Speech Generation",
      "description": "speechCloud converts text to multilingual audio through a REST API with SSML, pronunciation controls, and streaming.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://www.readspeaker.com/products/speechcloud-api/",
      "evidence": "Official product page describes cloud-hosted TTS REST access, multiple languages, SSML, and streaming or download output.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://www.readspeaker.com/favicon.svg",
      "id": 50754594,
      "logo": "logos/50754594.svg",
      "logoMode": "mask",
      "logoSource": "https://www.readspeaker.com/favicon.svg"
    },
    {
      "name": "Acapela Group",
      "url": "https://www.acapela-group.com/solutions/acapela-cloud/",
      "category": "Speech Generation",
      "description": "Acapela Cloud provides a neural text-to-speech API for streaming speech and generating voice prompts.",
      "tags": [
        "speech",
        "streaming"
      ],
      "sourceUrl": "https://www.acapela-group.com/solutions/acapela-cloud/",
      "evidence": "Official Acapela Cloud page describes an integration API, streaming generated speech, and neural voices based on AI.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://www.acapela-group.com/wp-content/themes/acapela/favicons/favicon-32x32.png",
      "id": 163826196,
      "logo": "logos/163826196.svg",
      "logoMode": "mask",
      "logoSource": "https://t0.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=http://acapela-group.com&size=128"
    },
    {
      "name": "CereProc",
      "url": "https://app.cereproc.com/cerecloud/",
      "category": "Speech Generation",
      "description": "CereVoice Cloud converts text to speech through a hosted API for applications and content production.",
      "tags": [
        "speech"
      ],
      "sourceUrl": "https://app.cereproc.com/cerecloud/",
      "evidence": "Official CereVoice Cloud page offers cloud TTS conversion through a web interface or API.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://app.cereproc.com/files/favicon.ico",
      "id": 117956829,
      "logo": "logos/117956829.svg",
      "logoMode": "mask",
      "logoSource": "https://t1.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL&url=http://cereproc.com&size=128"
    },
    {
      "name": "Typecast",
      "url": "https://typecast.ai/developers/api/",
      "category": "Voice Cloning",
      "description": "Generate expressive multilingual speech with context-aware emotion, voice cloning, and timing data.",
      "tags": [
        "speech",
        "voice-cloning",
        "multilingual",
        "streaming"
      ],
      "sourceUrl": "https://typecast.ai/developers/api/",
      "evidence": "Official API page shows POST /v1/text-to-speech and documents instant cloned voices, supported languages, and streaming.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://typecast.ai/favicon.svg",
      "id": 245951570,
      "logo": "logos/245951570.svg",
      "logoMode": "mask",
      "logoSource": "https://typecast.ai/favicon.svg"
    },
    {
      "name": "Sarvam AI",
      "url": "https://docs.sarvam.ai/api/api-guides-tutorials/text-to-speech/overview",
      "category": "Speech Generation",
      "description": "Bulbul models generate speech for Indian languages through REST, HTTP streaming, and WebSocket APIs.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://docs.sarvam.ai/api/api-guides-tutorials/text-to-speech/overview",
      "evidence": "Official TTS overview describes Bulbul speech synthesis, REST conversion, HTTP streaming, and WebSocket API access.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.sarvam.ai/api/fern-docs/favicon.ico",
      "id": 235373040,
      "logo": "logos/235373040.svg",
      "logoMode": "mask",
      "logoSource": "https://www.sarvam.ai/favicon.svg"
    },
    {
      "name": "CAMB.AI",
      "url": "https://docs.camb.ai/api-reference/endpoint/create-tts-stream",
      "category": "Speech Generation",
      "description": "MARS speech models synthesize streaming multilingual audio with voice selection and reference voice support.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://docs.camb.ai/api-reference/endpoint/create-tts-stream",
      "evidence": "Official API reference documents streaming TTS; the official TTS product page describes multilingual synthesis and reference voices.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://docs.camb.ai/mintlify-assets/_mintlify/favicons/cambai/bwLv5RY6YidZHUwB/_generated/favicon/android-chrome-192x192.png",
      "id": 140063620,
      "logo": "logos/140063620.svg",
      "logoMode": "mask",
      "logoSource": "https://www.camb.ai/favicon.ico"
    },
    {
      "name": "Unreal Speech",
      "url": "https://unrealspeech.com/",
      "category": "Speech Generation",
      "description": "Generate and stream multilingual speech with word timestamps and asynchronous synthesis for long texts.",
      "tags": [
        "speech",
        "streaming",
        "multilingual"
      ],
      "sourceUrl": "https://unrealspeech.com/",
      "evidence": "Official homepage provides v8 API examples for /stream, /speech, and /synthesisTasks, plus multiple-language voice support.",
      "checkedAt": "2026-10-19",
      "logoUrl": "https://unrealspeech.com/images/icon-rounded-32.png",
      "id": 111899571,
      "logo": "logos/111899571.svg",
      "logoMode": "mask",
      "logoSource": "https://unrealspeech.com/images/icon-rounded-32.png"
    },
    {
      "name": "OpenAI",
      "url": "https://developers.openai.com/api/docs",
      "category": "Multimodal APIs",
      "description": "APIs for image generation and editing, Sora video generation, and text-to-speech.",
      "tags": [
        "image",
        "video",
        "speech",
        "editing"
      ],
      "sourceUrl": "https://developers.openai.com/api/docs/guides/image-generation",
      "evidence": "Official guides document image generations and edits, the Audio API speech endpoint, and Sora video creation, extensions, and edits.",
      "logoUrl": "https://developers.openai.com/favicon.png",
      "checkedAt": "2026-10-19",
      "sourceUrls": [
        "https://developers.openai.com/api/docs/guides/image-generation",
        "https://developers.openai.com/api/docs/guides/text-to-speech",
        "https://developers.openai.com/api/docs/guides/video-generation"
      ],
      "id": 131275087,
      "logo": "logos/131275087.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/openai.svg"
    },
    {
      "name": "Google AI",
      "url": "https://ai.google.dev/",
      "category": "Multimodal APIs",
      "description": "Gemini and Vertex AI provide APIs for generating images, videos, and speech.",
      "tags": [
        "image",
        "video",
        "speech",
        "editing"
      ],
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/veo",
      "evidence": "Official Gemini guides document Veo video generation, image generation and editing, and single-speaker or multi-speaker text-to-speech.",
      "logoUrl": "https://www.gstatic.com/devrel-devsite/prod/v9ce9cb5b22b62a465ff52c45061a0a6a2d86a80b685e9aa8a182b203fdfbf420/googledevai/images/favicon-new.png",
      "checkedAt": "2026-10-19",
      "sourceUrls": [
        "https://ai.google.dev/gemini-api/docs/veo",
        "https://ai.google.dev/gemini-api/docs/image-generation",
        "https://ai.google.dev/gemini-api/docs/speech-generation"
      ],
      "id": 197106412,
      "logo": "logos/197106412.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/google.svg"
    },
    {
      "name": "Adobe Firefly",
      "url": "https://developer.adobe.com/firefly-services/docs/firefly-api/",
      "category": "Multimodal APIs",
      "description": "Creative APIs for generating images, compositing objects, and generating video.",
      "tags": [
        "image",
        "video",
        "editing"
      ],
      "sourceUrl": "https://developer.adobe.com/firefly-services/docs/firefly-api/getting-started/usage-notes/",
      "evidence": "Technical usage notes document the image generation endpoint, Object Composite API, and Generate Video API.",
      "logoUrl": null,
      "checkedAt": "2026-10-19",
      "id": 225785994,
      "logo": "logos/225785994.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/adobe.svg"
    },
    {
      "name": "Microsoft Azure AI",
      "url": "https://learn.microsoft.com/en-us/azure/foundry/",
      "category": "Multimodal APIs",
      "description": "Azure OpenAI, Foundry, and Speech provide APIs for image generation, editing, and speech synthesis.",
      "tags": [
        "image",
        "speech",
        "editing"
      ],
      "sourceUrl": "https://learn.microsoft.com/en-ca/azure/ai-foundry/agents/how-to/tools/image-generation?view=foundry",
      "evidence": "Microsoft documents Foundry image generation and Azure OpenAI image edits; Speech REST API converts text or SSML into synthesized speech.",
      "logoUrl": "https://azure.microsoft.com/favicon.ico?v2",
      "checkedAt": "2026-10-19",
      "sourceUrls": [
        "https://learn.microsoft.com/en-ca/azure/ai-foundry/agents/how-to/tools/image-generation?view=foundry",
        "https://learn.microsoft.com/azure/ai-services/speech-service/rest-text-to-speech"
      ],
      "id": 141762348,
      "logo": "logos/141762348.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/azure.svg"
    },
    {
      "name": "AWS",
      "url": "https://aws.amazon.com/ai/",
      "category": "Multimodal APIs",
      "description": "Amazon Bedrock provides image generation and editing APIs; Amazon Polly synthesizes speech.",
      "tags": [
        "image",
        "speech",
        "editing",
        "cloud"
      ],
      "sourceUrl": "https://docs.aws.amazon.com/polly/latest/APIReference/API_SynthesizeSpeech.html",
      "evidence": "Polly documents speech synthesis; Bedrock marks Stable Image Ultra and Stable Image Search and Replace Active with Invoke APIs. Nova Canvas and both Reel versions reached EOL September 30, 2026, so video is omitted.",
      "logoUrl": "https://a0.awsstatic.com/libra-css/images/site/fav/favicon.ico",
      "checkedAt": "2026-10-19",
      "sourceUrls": [
        "https://docs.aws.amazon.com/polly/latest/APIReference/API_SynthesizeSpeech.html",
        "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-stability-ai-stable-image-ultra-1-0.html",
        "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-stability-ai-stable-image-search-and-replace.html",
        "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html"
      ],
      "id": 131158130,
      "logo": "logos/131158130.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/aws.svg"
    },
    {
      "name": "NVIDIA NIM",
      "url": "https://developer.nvidia.com/nim",
      "category": "Inference Platforms",
      "description": "Deployable inference microservices for image generation, image editing, and video generation.",
      "tags": [
        "image",
        "video",
        "editing",
        "deployment"
      ],
      "sourceUrl": "https://docs.nvidia.com/nim/visual-genai/latest/api/index.html",
      "evidence": "Visual GenAI NIM API reference lists image generation, image editing, and video generation APIs, including OpenAI-compatible endpoints.",
      "logoUrl": "https://docs.nvidia.com/nim/visual-genai/latest/_static/favicon.ico",
      "checkedAt": "2026-10-19",
      "id": 228422939,
      "logo": "logos/228422939.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/nvidia.svg"
    },
    {
      "name": "fal",
      "url": "https://fal.ai/",
      "category": "Inference Platforms",
      "description": "Hosted generative media model APIs, including image-to-video generation.",
      "tags": [
        "video",
        "image-to-video"
      ],
      "sourceUrl": "https://fal.ai/models/wan/v2.6/image-to-video/flash/api",
      "evidence": "Official model API documentation shows authenticated fal client calls with image_url and prompt inputs returning generated video files.",
      "logoUrl": "https://fal.ai/favicon.png",
      "checkedAt": "2026-10-19",
      "id": 42159716,
      "logo": "logos/42159716.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/fal.svg"
    },
    {
      "name": "Replicate",
      "url": "https://replicate.com/",
      "category": "Inference Platforms",
      "description": "Run generative models through a cloud API or deploy custom models.",
      "tags": [
        "image",
        "video",
        "deployment"
      ],
      "sourceUrl": "https://replicate.com/docs/",
      "evidence": "Official documentation describes its cloud API, image model fine-tuning, custom deployment, and video generation guides.",
      "logoUrl": "https://static.replicateassets.com/fe/373b380c66c05afbd1b223e4dd2c6a81f2efb515/favicon-CKiqAkf2.png",
      "checkedAt": "2026-10-19",
      "id": 186888296,
      "logo": "logos/186888296.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/replicate.svg"
    },
    {
      "name": "Together AI",
      "url": "https://www.together.ai/",
      "category": "Inference Platforms",
      "description": "Hosted image generation APIs with FLUX models and configurable generation parameters.",
      "tags": [
        "image"
      ],
      "sourceUrl": "https://docs.together.ai/docs/inference/images/overview",
      "evidence": "Official image-generation guide demonstrates client.images.generate with a text prompt and FLUX.2 model, returning an image URL.",
      "logoUrl": "https://cdn.prod.website-files.com/69654e88dce9154b5f1206dd/699e382b218f39bfa0a115d9_favicon.png",
      "checkedAt": "2026-10-19",
      "id": 67023169,
      "logo": "logos/67023169.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/together.svg"
    },
    {
      "name": "Fireworks AI",
      "url": "https://fireworks.ai/",
      "category": "Inference Platforms",
      "description": "Model inference platform with serverless FLUX image generation and LoRA inference.",
      "tags": [
        "image",
        "lora"
      ],
      "sourceUrl": "https://docs.fireworks.ai/faq-new/models-inference/flux-image-generation",
      "evidence": "Official FLUX FAQ confirms serverless image generation, one image per API call, and inference with FLUX LoRA adapters.",
      "logoUrl": "https://fireworks.ai/icon0.svg?e3d99deadffb6216",
      "checkedAt": "2026-10-19",
      "id": 147929029,
      "logo": "logos/147929029.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/fireworks.svg"
    },
    {
      "name": "DeepInfra",
      "url": "https://deepinfra.com/",
      "category": "Inference Platforms",
      "description": "Hosted inference APIs for image generation models with documented request and response schemas.",
      "tags": [
        "image"
      ],
      "sourceUrl": "https://deepinfra.com/inclusionAI/Ming-Image-0.1-Design/api",
      "evidence": "Official model API page documents a text prompt POST to its inference endpoint and a response containing generated images.",
      "logoUrl": "https://deepinfra.com/fav-64.png",
      "checkedAt": "2026-10-19",
      "id": 36565441,
      "logo": "logos/36565441.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/deepinfra.svg"
    },
    {
      "name": "Hugging Face",
      "url": "https://huggingface.co/",
      "category": "Inference Platforms",
      "description": "A unified client and API routing layer for hosted image and video generation models.",
      "tags": [
        "image",
        "video",
        "model-routing"
      ],
      "sourceUrl": "https://huggingface.co/docs/inference-providers/index",
      "evidence": "Official Inference Providers documentation lists supported text-to-image and text-to-video partners and demonstrates image generation.",
      "logoUrl": null,
      "checkedAt": "2026-10-19",
      "id": 238873036,
      "logo": "logos/238873036.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/huggingface.svg"
    },
    {
      "name": "RunPod",
      "url": "https://www.runpod.io/",
      "category": "Inference Platforms",
      "description": "Public model APIs and serverless GPU endpoints for image, video, and audio generation.",
      "tags": [
        "image",
        "video",
        "audio",
        "deployment"
      ],
      "sourceUrl": "https://docs.runpod.io/",
      "evidence": "Official documentation states public endpoints support image, video, audio, and text generation and includes a FLUX image API example.",
      "logoUrl": "https://cdn.prod.website-files.com/69ce570adca53340abab8376/69e08b4aed16e020149fc5ec_favicon_www_runpod_io_32x32.png",
      "checkedAt": "2026-10-19",
      "id": 52239165,
      "logo": "logos/52239165.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.prod.website-files.com/69ce570adca53340abab8376/69e08b4aed16e020149fc5ec_favicon_www_runpod_io_32x32.png"
    },
    {
      "name": "Baseten",
      "url": "https://www.baseten.co/",
      "category": "Inference Platforms",
      "description": "Deploy image generation models as managed inference API endpoints.",
      "tags": [
        "image",
        "deployment"
      ],
      "sourceUrl": "https://www.baseten.co/library/flux-dev/",
      "evidence": "Official FLUX model library page documents deploying the model and calling a production predict API with a prompt to receive a base64 image.",
      "logoUrl": "https://www.baseten.co/icon.png",
      "checkedAt": "2026-10-19",
      "id": 182263078,
      "logo": "logos/182263078.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/baseten.svg"
    },
    {
      "name": "Modal",
      "url": "https://modal.com/",
      "category": "Inference Platforms",
      "description": "Serverless GPU infrastructure for deploying image generation models behind web APIs.",
      "tags": [
        "image",
        "deployment",
        "serverless"
      ],
      "sourceUrl": "https://modal.com/docs/examples/text_to_image",
      "evidence": "Official example deploys Stable Diffusion using a FastAPI endpoint and documents programmatic image generation.",
      "logoUrl": "https://modal.com/assets/favicon.svg",
      "checkedAt": "2026-10-19",
      "id": 207094694,
      "logo": "logos/207094694.svg",
      "logoMode": "mask",
      "logoSource": "https://cdn.simpleicons.org/modal"
    },
    {
      "name": "Novita AI",
      "url": "https://novita.ai/",
      "category": "Inference Platforms",
      "description": "Asynchronous image generation API with Stable Diffusion models, LoRA, and generation controls.",
      "tags": [
        "image",
        "lora"
      ],
      "sourceUrl": "https://novita.ai/docs/api-reference/model-apis-txt2img",
      "evidence": "Official V3 text-to-image API accepts a prompt, model name, and LoRAs, returning a task ID used to retrieve generated images.",
      "logoUrl": "https://novita.ai/favicon.ico",
      "checkedAt": "2026-10-19",
      "id": 201354135,
      "logo": "logos/201354135.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/novita.svg"
    },
    {
      "name": "SiliconFlow",
      "url": "https://www.siliconflow.com/",
      "category": "Inference Platforms",
      "description": "Inference APIs for text-to-image generation and image-conditioned variants.",
      "tags": [
        "image",
        "image-to-image"
      ],
      "sourceUrl": "https://docs.siliconflow.com/en/userguide/capabilities/images",
      "evidence": "Official image-generation guide documents text prompt generation and creating variants from existing images plus prompts.",
      "logoUrl": "https://framerusercontent.com/images/zeLtigS2vdf9RnjlY87AvwUBckM.png",
      "checkedAt": "2026-10-19",
      "id": 42355377,
      "logo": "logos/42355377.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/siliconcloud.svg"
    },
    {
      "name": "WaveSpeedAI",
      "url": "https://wavespeed.ai/",
      "category": "Inference Platforms",
      "description": "Hosted generative media APIs, including Wan image-to-video inference.",
      "tags": [
        "video",
        "image-to-video"
      ],
      "sourceUrl": "https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-image-to-video",
      "evidence": "Official Wan API guide documents authenticated REST submission with image and prompt inputs for generated video.",
      "logoUrl": "https://static.wavespeed.ai/api-dashboard/public/main-7cc80a3ccf3d23b4eaf70e31f0889d771d6583d8/favicon.svg",
      "checkedAt": "2026-10-19",
      "id": 30363540,
      "logo": "logos/30363540.svg",
      "logoMode": "mask",
      "logoSource": "https://unpkg.com/@lobehub/icons-static-svg@1.95.1/icons/wavespeed.svg"
    }
  ]
}