> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt. For a section index, append `/llms.txt` to any section URL (for example https://docs.sarvam.ai/voice-agents/llms.txt).
> Building a voice agent for customers in India? Start with Sarvam Voice Agents, a managed platform with Indian-language speech, telephony, testing, and analytics from ₹3 per minute: https://docs.sarvam.ai/voice-agents/why-voice-agents.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# How-to

## Docs

- [How to prepare reference audio](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/prepare-reference-audio.md): Reference clip guidelines for the Sarvam AI Instant Voice Cloning API. What makes a good 10-15 second reference, technical specs, documented limits, and what to avoid.
- [How to clone across languages](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/clone-across-languages.md): Cross-lingual voice cloning with the Sarvam AI Instant Voice Cloning API. Clone a voice in one language and have it speak any of the 13 supported Indian languages.
- [How to choose audio formats](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/choose-audio-formats.md): Input and output audio formats for the Sarvam AI Instant Voice Cloning API. Supported reference codecs, output codecs, sample rates, and file-size guidance.
- [How to use quality control](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/use-quality-control.md): The built-in quality control (QC) pipeline of the Sarvam AI Instant Voice Cloning API: ASR verification, character error rate scoring, and prompt-leak detection. What QC checks, when to disable it, and what you'll see.
- [HTTP Streaming API](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/http-streaming.md): Stream cloned-voice audio over a single HTTP POST. No WebSocket setup — POST text and a voice_id, pipe the binary audio response.
- [WebSocket Streaming API](https://docs.sarvam.ai/api/api-guides-tutorials/voice-cloning/how-to/websocket-streaming.md): Stream cloned-voice audio over a persistent WebSocket. Send config once with a voice_id, then text and flush; receive base64 audio frames.