{
  "slug": "transcribe-audio",
  "label": "transcribe audio",
  "blurb": "Turn recordings, meetings and live audio into text.",
  "keywords": [
    "transcription",
    "transcribe",
    "speech-to-text",
    "speech recognition"
  ],
  "categories": [
    "voice-messaging",
    "language"
  ],
  "access": [
    "api"
  ],
  "count": 12,
  "official": 5,
  "url": "https://agentswitchboard.dev/tasks/transcribe-audio",
  "browseUrl": "https://agentswitchboard.dev/browse?task=transcribe-audio",
  "agentsUrl": "https://agentswitchboard.dev/api/agents?task=transcribe-audio",
  "agents": [
    {
      "name": "Vidmoat",
      "slug": "vidmoat",
      "url": "https://agentswitchboard.dev/agents/vidmoat",
      "iconUrl": "https://agentswitchboard.dev/icons/vidmoat.png?v=cb397da9",
      "description": "Edits video programmatically from agents over a remote MCP server and a REST v1 API: import media, run timeline commands, preview frames, transcribe and render MP4s. OAuth or Bearer key required.",
      "provider": "Buzz Innovations Ltd",
      "categories": [
        "content-media",
        "voice-messaging"
      ],
      "accessMethods": [
        "api",
        "mcp"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Transcription: Transcribes uploaded audio and video via POST /ai/transcriptions, returning a job polled at /ai/jobs/{id}."
    },
    {
      "name": "AssemblyAI",
      "slug": "assemblyai",
      "url": "https://agentswitchboard.dev/agents/assemblyai",
      "iconUrl": "https://agentswitchboard.dev/icons/assemblyai.png?v=7d6c5a54",
      "description": "Speech recognition API with real-time and batch transcription plus audio intelligence models for summarization, topic detection, and redaction.",
      "provider": "AssemblyAI",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Deepgram",
      "slug": "deepgram",
      "url": "https://agentswitchboard.dev/agents/deepgram",
      "iconUrl": "https://agentswitchboard.dev/icons/deepgram.png?v=34d0f9eb",
      "description": "Speech-to-text and voice AI API with real-time streaming transcription, speaker diarization, and text-to-speech for voice agents.",
      "provider": "Deepgram",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Cartesia",
      "slug": "cartesia",
      "url": "https://agentswitchboard.dev/agents/cartesia",
      "iconUrl": "https://agentswitchboard.dev/icons/cartesia.png?v=d81b9acb",
      "description": "Delivers ultra-low-latency text-to-speech and speech-to-text through the Sonic model family, with a voice-agent framework and streaming WebSocket API.",
      "provider": "Cartesia",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Speech Recognition: Transcribes streaming audio to text, feeding live user speech into an agent loop as it is spoken."
    },
    {
      "name": "Fish Audio",
      "slug": "fish-audio",
      "url": "https://agentswitchboard.dev/agents/fish-audio",
      "iconUrl": "https://agentswitchboard.dev/icons/fish-audio.png?v=b7c4fa20",
      "description": "Generates speech, clones voices and transcribes audio through REST and WebSocket APIs backed by open-weight models, for developers building voice apps and phone agents.",
      "provider": "Fish Audio",
      "categories": [
        "voice-messaging",
        "content-media"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Speech to Text: Transcribes audio, including multi-speaker conversations with speaker turns."
    },
    {
      "name": "Meta Model API",
      "slug": "meta-model-api",
      "url": "https://agentswitchboard.dev/agents/meta-model-api",
      "iconUrl": "https://agentswitchboard.dev/icons/meta-model-api.png?v=8bdadce3",
      "description": "Serves Meta's Muse Spark, Muse Image, Muse Voice Transcribe, and SAM models through Responses, Chat Completions, and Messages-compatible APIs for app and agent developers.",
      "provider": "Meta",
      "categories": [
        "language",
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Speech To Text: Transcribes live audio over WebSocket or uploaded files with Muse Voice Transcribe, with speaker labels."
    },
    {
      "name": "Sarvam AI API",
      "slug": "sarvam-ai",
      "url": "https://agentswitchboard.dev/agents/sarvam-ai",
      "iconUrl": "https://agentswitchboard.dev/icons/sarvam-ai.png?v=9abd46a4",
      "description": "Transcribes, synthesizes, translates, and chats in Indian languages and English with Sarvam's Saaras, Bulbul, Mayura, and Sarvam-105B models, via REST, WebSocket, SDKs, and MCP.",
      "provider": "Sarvam AI",
      "categories": [
        "language",
        "voice-messaging"
      ],
      "accessMethods": [
        "api",
        "mcp"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Saaras v3 Speech-to-Text: Transcribes, translates, and captions code-mixed and regional Indian speech in real time or in batch."
    },
    {
      "name": "Voicebox",
      "slug": "voicebox",
      "url": "https://agentswitchboard.dev/agents/voicebox",
      "iconUrl": "https://agentswitchboard.dev/icons/voicebox.png?v=3678712c",
      "description": "Runs a local voice studio for voice cloning, text-to-speech and Whisper dictation, and lets agents speak or transcribe through a built-in MCP server and REST API.",
      "provider": "Jamie Pine",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "mcp",
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "none",
      "why": "Whisper Transcription: Transcribes audio with OpenAI Whisper on MLX or PyTorch, exposed through the /transcribe endpoint and the voicebox_transcribe…"
    },
    {
      "name": "MiniMax API Platform",
      "slug": "minimax-api",
      "url": "https://agentswitchboard.dev/agents/minimax-api",
      "iconUrl": "https://agentswitchboard.dev/icons/minimax-api.png?v=07c1b80c",
      "description": "Serves MiniMax's M-series coding and agent models through Anthropic- and OpenAI-compatible APIs, plus video, speech, image and music generation, for developers building agents.",
      "provider": "MiniMax AI",
      "categories": [
        "language",
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Text to Speech and Voice Cloning: Synthesizes speech over HTTP or streaming WebSocket and clones or designs custom voices."
    },
    {
      "name": "Hugging Face Inference Providers",
      "slug": "hugging-face-inference-providers",
      "url": "https://agentswitchboard.dev/agents/hugging-face-inference-providers",
      "iconUrl": "https://agentswitchboard.dev/icons/hugging-face-inference-providers.png?v=cdb9e63c",
      "description": "Routes open-model inference across partner providers such as Groq, Together, and Fireworks with one Hugging Face token, via an OpenAI-compatible API and Python and JS SDKs.",
      "provider": "Hugging Face",
      "categories": [
        "language",
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "bearer",
      "why": "Speech to Text: Transcribes audio with speech recognition models on supported providers."
    },
    {
      "name": "Speko",
      "slug": "speko",
      "url": "https://agentswitchboard.dev/agents/speko",
      "iconUrl": "https://agentswitchboard.dev/icons/speko.png?v=a0b93298",
      "description": "Unified routing API for voice models across providers, giving voice agents one interface for speech-to-text, text-to-speech, and fallback. Y Combinator S26.",
      "provider": "Speko",
      "categories": [
        "voice-messaging",
        "infrastructure"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Vapi",
      "slug": "vapi",
      "url": "https://agentswitchboard.dev/agents/vapi",
      "iconUrl": "https://agentswitchboard.dev/icons/vapi.png?v=7c77cf20",
      "description": "Voice AI platform for building production phone agents. Handles real-time STT, TTS, turn-taking, and LLM orchestration. Scalable to millions of concurrent calls.",
      "provider": "Vapi",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Record, transcribe, and analyze every call with structured JSON summaries"
    }
  ],
  "relatedTasks": [
    "build-a-voice-agent",
    "make-phone-calls",
    "translate-text"
  ],
  "stacks": [
    "realtime-voice-agent"
  ]
}