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

# Models

## Docs

- [Overview](https://docs.hams.ai/models/overview.md): HAMS's real-time speech models, the two WebSocket endpoints that expose them, and what a client needs to use them.
- [Authentication and limits](https://docs.hams.ai/models/authentication.md): How to present your API key on a WebSocket connection, how many connections you can hold, and what to do on each error.
- [Speech-to-text](https://docs.hams.ai/models/speech-to-text.md): Stream 16 kHz PCM audio to the recognizer and receive interim and final transcripts as JSON.
- [Text-to-speech](https://docs.hams.ai/models/text-to-speech.md): Send text, receive 24 kHz PCM audio frames as each sentence is synthesized, with natural pauses, cancellation and per-request completion messages.