{
  "slug": "build-a-voice-agent",
  "label": "build a voice agent",
  "blurb": "Speech-to-text, text-to-speech and real-time frameworks for agents you talk to.",
  "keywords": [
    "voice agent",
    "voice ai",
    "text-to-speech",
    "speech-to-text",
    "realtime voice"
  ],
  "categories": [
    "voice-messaging"
  ],
  "access": [
    "api"
  ],
  "count": 19,
  "official": 6,
  "url": "https://agentswitchboard.dev/tasks/build-a-voice-agent",
  "browseUrl": "https://agentswitchboard.dev/browse?task=build-a-voice-agent",
  "agentsUrl": "https://agentswitchboard.dev/api/agents?task=build-a-voice-agent",
  "agents": [
    {
      "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 Synthesis: Generates natural speech from text with latency low enough for real-time conversational voice agents."
    },
    {
      "name": "LiveKit Agents",
      "slug": "livekit-agents",
      "url": "https://agentswitchboard.dev/agents/livekit-agents",
      "iconUrl": "https://agentswitchboard.dev/icons/livekit-agents.png?v=14116536",
      "description": "Builds production realtime voice and video AI agents with WebRTC transport, turn detection, and STT/LLM/TTS pipelines. Python and Node framework by LiveKit.",
      "provider": "LiveKit",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Realtime Voice Agents: Builds production voice and video agents that stream over WebRTC with low latency."
    },
    {
      "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": "Text to Speech: Converts text to speech with emotion tags and fine-grained pronunciation control, over REST or real-time WebSocket."
    },
    {
      "name": "TEN Framework",
      "slug": "ten-framework",
      "url": "https://agentswitchboard.dev/agents/ten-framework",
      "iconUrl": "https://agentswitchboard.dev/icons/ten-framework.png?v=d9ec8dae",
      "description": "Builds realtime conversational voice AI agents with a low-latency, multimodal framework in C, Go, and Python. Handles audio, video, and data streams. Open source.",
      "provider": "TEN",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api",
        "cli"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Realtime Voice: Builds low-latency conversational voice agents that stream audio in and out in real time."
    },
    {
      "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": "Build production voice agents for inbound and outbound phone calls with sub-500ms latency"
    },
    {
      "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": "Agent Voice Output: Lets any MCP-aware agent speak in a cloned voice via the voicebox_speak tool or POST /speak, with a per-agent voice binding."
    },
    {
      "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": "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": "Pipecat",
      "slug": "pipecat",
      "url": "https://agentswitchboard.dev/agents/pipecat",
      "iconUrl": "https://agentswitchboard.dev/icons/pipecat.png?v=ea01438e",
      "description": "Builds realtime voice and multimodal conversational agents in Python — orchestrates STT, LLM, and TTS pipelines with interruption handling. Open-source framework by Daily.",
      "provider": "Daily",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": "Voice Pipeline Orchestration: Chains STT, LLM, and TTS services into a realtime voice pipeline for conversational agents."
    },
    {
      "name": "Dograh",
      "slug": "dograh",
      "url": "https://agentswitchboard.dev/agents/dograh",
      "iconUrl": "https://agentswitchboard.dev/icons/dograh.png?v=5c8f82ae",
      "description": "Builds and self-hosts voice AI agents with a visual workflow builder, telephony, and bring-your-own-key speech-to-speech or LLM, STT, and TTS pipelines.",
      "provider": "Dograh HQ",
      "categories": [
        "voice-messaging",
        "orchestration"
      ],
      "accessMethods": [
        "api",
        "mcp"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "name": "Retell AI",
      "slug": "retell-ai",
      "url": "https://agentswitchboard.dev/agents/retell-ai",
      "iconUrl": "https://agentswitchboard.dev/icons/retell-ai.png?v=25541240",
      "description": "Builds, tests, deploys, and monitors natural-sounding AI voice agents with ~600ms latency for scheduling, support, and administrative phone workflows.",
      "provider": "Retell AI",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": null
    },
    {
      "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": "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": null
    },
    {
      "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": "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": "Wonderful",
      "slug": "wonderful-ai",
      "url": "https://agentswitchboard.dev/agents/wonderful-ai",
      "iconUrl": "https://agentswitchboard.dev/icons/wonderful-ai.png?v=a9cc28a1",
      "description": "Enterprise voice AI platform with pre-trained agents for phone, chat, and email. Covers 40+ languages, integrates with Salesforce, SAP, and ServiceNow, with seamless escalation to human agents.",
      "provider": "Wonderful AI",
      "categories": [
        "customer-support"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "oauth2",
      "why": "Deploy production-ready voice agents across inbound and outbound phone channels with natural, low-latency conversation"
    },
    {
      "name": "MiniMax MCP",
      "slug": "minimax-mcp",
      "url": "https://agentswitchboard.dev/agents/minimax-mcp",
      "iconUrl": "https://agentswitchboard.dev/icons/minimax-mcp.png?v=138accd8",
      "description": "Official MiniMax AI MCP server — generate speech from text, clone voices, create images and videos, and compose music via a single interface.",
      "provider": "MiniMax AI",
      "categories": [
        "content-media"
      ],
      "accessMethods": [
        "mcp",
        "cli"
      ],
      "verified": true,
      "official": true,
      "featured": false,
      "authType": "apiKey",
      "why": "Text to Speech: Converts text to natural-sounding audio using a library of built-in voices or custom voice profiles."
    },
    {
      "name": "Bland AI",
      "slug": "bland-ai",
      "url": "https://agentswitchboard.dev/agents/bland-ai",
      "iconUrl": "https://agentswitchboard.dev/icons/bland-ai.png?v=72e7a1a4",
      "description": "Deploys enterprise AI phone agents that handle inbound and outbound calls in 40+ languages with SOC2, HIPAA, and PCI DSS compliance built in.",
      "provider": "Bland",
      "categories": [
        "voice-messaging"
      ],
      "accessMethods": [
        "api"
      ],
      "verified": true,
      "official": false,
      "featured": false,
      "authType": "apiKey",
      "why": null
    }
  ],
  "relatedTasks": [
    "transcribe-audio",
    "make-phone-calls",
    "make-videos"
  ],
  "stacks": [
    "realtime-voice-agent"
  ]
}