> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://murf.ai/api/docs/speech-to-text/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://murf.ai/api/docs/_mcp/server.

# Speech to Text (Beta)

## Docs

- [Speech to Text (Beta)](https://murf.ai/api/docs/speech-to-text/overview.md): Murf Speech to Text streams audio over a WebSocket and returns partial and final transcripts with word-level timestamps, built for voice agents and telephony.
- [Streaming](https://murf.ai/api/docs/speech-to-text/streaming.md): Connect to the Murf Speech to Text WebSocket, stream audio, manage turns with Finalize, and handle partial and final transcripts.
- [Audio Formats](https://murf.ai/api/docs/speech-to-text/audio-formats.md): Declare your input audio format with AudioConfig. Murf Speech to Text accepts PCM, µ-law, A-law and Opus at 8 kHz to 48 kHz.
- [Languages](https://murf.ai/api/docs/speech-to-text/languages.md): Murf Speech to Text supports English (India) and 11 Indian languages, with automatic language detection.
- [Keyword Boosting](https://murf.ai/api/docs/speech-to-text/keyword-boosting.md): Use the keywords and alpha parameters to bias Murf Speech to Text towards words your callers are likely to say.
- [Errors](https://murf.ai/api/docs/speech-to-text/errors.md): How Murf Speech to Text reports errors, what each WebSocket close code means, and how to handle it.