# Nari Labs | Documentation

## 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.narilabs.com/_mcp/server

## Docs

- [Nari Labs API](https://docs.narilabs.com/overview.md): Multimodal inference at the speed of light.
- [TTS quickstart](https://docs.narilabs.com/quickstart.md): Make your first TTS request and save the result as a WAV file.
- [STT quickstart](https://docs.narilabs.com/stt-quickstart.md): Stream your first audio sample and receive a transcript.
- [Authentication](https://docs.narilabs.com/authentication.md): Authenticate API requests with a Nari API key.
- [Generate speech](https://docs.narilabs.com/generate-speech.md): Send text, receive audio, and understand request limits and usage.
- [Streaming audio](https://docs.narilabs.com/streaming-audio.md): Receive and play speech as it is generated.
- [TTS input streaming](https://docs.narilabs.com/streaming-text.md): Send text incrementally and receive audio chunks as they are generated.
- [Voices and languages](https://docs.narilabs.com/voices.md): Discover voices for your model and use their assigned language.
- [Realtime transcription](https://docs.narilabs.com/transcribe-audio.md): Stream audio and receive partial and final transcripts over WebSocket.
- [Transcripts and turn detection](https://docs.narilabs.com/transcripts-and-turn-detection.md): Update partial text and choose when an utterance is complete.
- [Models and pricing](https://docs.narilabs.com/models-and-pricing.md): Choose the right model for your latency and cost requirements.
- [Rate limits](https://docs.narilabs.com/rate-limits.md): Understand organization concurrency limits.
- [Usage and billing](https://docs.narilabs.com/usage-and-billing.md): Understand usage measurements and credit deductions.
- [Organizations and members](https://docs.narilabs.com/organizations.md): Manage members, roles, seats, and invitations.
- [Request logs](https://docs.narilabs.com/request-logs.md): Review API activity and identify requests.
- [Errors and troubleshooting](https://docs.narilabs.com/errors.md): Identify errors and decide when to retry.
- [API reference](https://docs.narilabs.com/api-reference.md): Request parameters, responses, and events for the Nari API.

## 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)