# 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.

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.kotoba.tech/_mcp/server

## Docs

- [Kotoba Technologies APIs](https://docs.kotoba.tech/overview/introduction.md): Low-latency speech APIs for real-time and async applications.
- [Authentication](https://docs.kotoba.tech/overview/authentication.md): Two ways to authenticate against the Kotoba Realtime APIs.
- [Audio formats](https://docs.kotoba.tech/overview/audio-formats.md): Supported input and output encodings.
- [Speech to Text](https://docs.kotoba.tech/overview/capabilities/speech-to-text.md): Stream live transcripts or transcribe finished audio files.
- [Speech to Speech Translation](https://docs.kotoba.tech/overview/capabilities/speech-to-speech.md): Translate spoken audio into spoken audio in another language.
- [Text to Speech](https://docs.kotoba.tech/overview/capabilities/text-to-speech.md): Synthesize natural speech from text, with streaming output.
- [Python SDK — s2t](https://docs.kotoba.tech/s2t/python-sdk.md): Speech-to-text from Python, REST batch + WebSocket streaming.
- [Python SDK — s2st](https://docs.kotoba.tech/s2st/python-sdk.md): Speech-to-speech translation from Python, WebSocket streaming.
- [Python SDK — t2s](https://docs.kotoba.tech/t2s/python-sdk.md): Text-to-speech from Python, with one-shot and streaming synthesis.

## API Docs

- Live (WebSocket) > ASR [asr](https://docs.kotoba.tech/s2t/streaming/asr/asr.md)
- Batch (REST) > Transcription API [Submit an audio file for asynchronous transcription.](https://docs.kotoba.tech/s2t/batch/transcription-api/submit-transcription-job-v-1-transcription-jobs-post.md)
- Batch (REST) > Transcription API [Fetch the transcription result for a completed job.](https://docs.kotoba.tech/s2t/batch/transcription-api/get-transcription-job-v-1-transcription-jobs-job-id-get.md)
- Live (WebSocket) > Sts [sts](https://docs.kotoba.tech/s2st/streaming/sts/sts.md)
- Live (WebSocket) > TTS [tts](https://docs.kotoba.tech/t2s/streaming/tts/tts.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.kotoba.tech/openapi.json)
- [OpenAPI YAML](https://docs.kotoba.tech/openapi.yaml)


## AsyncAPI Specification

The raw AsyncAPI 2.6.0 specification for the WebSocket channels is available at:
- [AsyncAPI JSON](https://docs.kotoba.tech/asyncapi.json)
- [AsyncAPI YAML](https://docs.kotoba.tech/asyncapi.yaml)