> **voice-agent** — skill 14 of 14 in [deepgram/skills](https://skillsdocs.com/deepgram/skills).
>
> Book (all skills, one file): https://skillsdocs.com/deepgram/skills.md
> Machine manifest: https://skillsdocs.com/deepgram/skills/.well-known/agent-skills/index.json
> Install the book: `npx skills add deepgram/skills`
> Upstream: https://github.com/deepgram/skills/blob/main/skills/voice-agent/SKILL.md @ `main`
> Raw bytes, no header: https://raw.githubusercontent.com/deepgram/skills/main/skills/voice-agent/SKILL.md
> Base for relative paths: https://raw.githubusercontent.com/deepgram/skills/main/skills/voice-agent/
> Licence: No licence detected — all rights reserved by its authors
>
> Content © its authors. This skill's body is not served here; the links above are. Takedown: https://github.com/DreambaseAI/skillsdocs/issues/new?labels=takedown&title=Takedown+request

# voice-agent

Build a real-time voice agent on Deepgram's Voice Agent API: one WebSocket at wss://agent.deepgram.com/v1/agent/converse that runs speech-to-text, a language model (Deepgram-hosted or your own endpoint), and text-to-speech, with barge-in, mid-call updates, and function calling that your own client executes. Use when someone says "voice agent", "voice bot", "speech-to-speech", "talk to an AI on the phone", "agent.deepgram.com", "Settings message", "FunctionCallRequest", "barge-in", "Twilio voice agent", or asks whether to build on Deepgram directly or through LiveKit Agents, Pipecat, Vapi, or Retell. Routes to the api, docs, starters, recipes, examples, and per-language SDK skills for the full reference.

No licence could be detected for this skill at either the repository or the skill level, so its body is not reproduced here. Read it upstream:

https://raw.githubusercontent.com/deepgram/skills/main/skills/voice-agent/SKILL.md