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

# Kotoba — the foundational voice AI model for a borderless world

> Kotoba is a frontier voice AI company building a real-time speech model and simultaneous translation technology. Build with the ASR, STS, and TTS realtime APIs.

# Kotoba Technologies Realtime APIs

Kotoba is a frontier voice AI company. Its realtime APIs let you stream audio
over WebSocket and receive transcription, translation, or synthesized speech.

* **s2t** — Speech to Text. See `/s2t/python-sdk`, `/s2t/streaming` (live), and `/s2t/batch` (REST).
* **s2st** — Speech to Speech Translation. See `/s2st/python-sdk` and `/s2st/streaming`.
* **t2s** — Text to Speech. See `/t2s/python-sdk` and `/t2s/streaming`.

Kotoba APIs are in private alpha — access is limited to selected customers
(contact [kotoba\_product@kotoba.tech](mailto:kotoba_product@kotoba.tech)).

Install the SDK:

```bash
pip install kotoba-sdk
```

See `/overview/introduction` for the quickstart, authentication, and audio-format reference.