# Typeless API

> Speech-to-text API with built-in LLM refinement

## Docs

- [Authentication](https://docs.typelessapi.com/authentication.md): Authenticate requests with your Typeless API key
- [Pre-recorded audio](https://docs.typelessapi.com/guides/pre-recorded.md): Transcribe audio files synchronously — voice notes, meeting clips, and voicemail returned in a single blocking request.
- [Streaming audio](https://docs.typelessapi.com/guides/streaming.md): Send raw PCM frames over WebSocket and receive a final, LLM-refined transcript when the stream ends
- [Introduction](https://docs.typelessapi.com/introduction.md): Speech-to-text API with built-in LLM refinement — get polished, ready-to-use transcripts, not raw ASR output
- [Models & Pricing](https://docs.typelessapi.com/models-pricing.md): Choose the right Typeless ASR model for your accuracy and cost requirements
- [Quickstart](https://docs.typelessapi.com/quickstart.md): Transcribe your first audio file in 5 minutes
- [Errors](https://docs.typelessapi.com/reference/errors.md): Error envelope, full list of error codes, retry guidance, and WebSocket error delivery.
- [API Reference](https://docs.typelessapi.com/reference/overview.md): Core conventions shared by every Typeless API endpoint — base URL, authentication, response shape, and status codes.
- [Rate limits](https://docs.typelessapi.com/reference/rate-limits.md): Default per-account limits for request rate, WebSocket concurrency, and audio size, plus retry guidance.
- [Transcribe audio](https://docs.typelessapi.com/reference/transcribe.md): Submit a pre-recorded audio file and receive a refined transcript with usage metadata.
- [Stream transcription](https://docs.typelessapi.com/reference/transcribe-stream.md): WebSocket protocol reference for real-time PCM audio streaming and transcription.