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

# API Reference


## API Docs

- Text to Speech > Voices [List voices](https://docs.narilabs.com/api-reference/text-to-speech/voices/list-voices.md)
- Text to Speech > Speech [Generate speech](https://docs.narilabs.com/api-reference/text-to-speech/speech/generate-speech.md)
- Text to Speech > Input Stream [Stream text to speech](https://docs.narilabs.com/api-reference/text-to-speech/input-stream/stream-text-to-speech.md)
- Speech to Text > Realtime [Realtime transcription](https://docs.narilabs.com/api-reference/speech-to-text/realtime/realtime-transcription.md)

## OpenAPI Specification

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


## AsyncAPI Specification

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


> **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page.

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

# API reference

#### [Text to Speech](/api-reference/text-to-speech/speech/generate-speech)

Convert text to audio.

`POST /v1/audio/speech`

#### [TTS input streaming](/api-reference/text-to-speech/input-stream/stream-text-to-speech)

Stream text and receive PCM audio.

`WSS /v1/text-to-speech/{voice_id}/stream-input`

#### [Speech to Text](/api-reference/speech-to-text/realtime/realtime-transcription)

Stream audio and receive partial and final transcripts.

`WSS /v1/realtime?intent=transcription`

Authenticate with `Authorization: Bearer <NARI_API_KEY>`. See [Authentication](/authentication).