# Glot Labs API Documentation

> Build real-time and batch Speech-to-Text, Text-to-Speech, translation, and speech intelligence workflows with the Glot Labs API.

- API base URL: https://api.glotlabs.ai
- Authentication: `Authorization: Bearer YOUR_API_KEY`
- Recommended starting point: `wss://api.glotlabs.ai/v1/realtime/asr`
- Automatic language detection: omit `language` or set it to `auto`
- Coverage: 181 languages, dialects, and variants overall; availability varies by endpoint
- Each link below returns clean Markdown suitable for LLM context.

## Getting Started

- [Welcome to Glot Labs](https://glotlabs.ai/docs/index.md): Glot Labs is an AI-powered audio and text processing platform. Build real-time and batch speech workflows, translation, annotation, and text analysis through a consistent API.
- [Quickstart](https://glotlabs.ai/docs/quickstart/index.md): Get up and running with the Glot Labs API in under 5 minutes.
- [Authentication](https://glotlabs.ai/docs/authentication/index.md): All API endpoints require authentication via an API key.

## Live

- [Real-time Transcription (Speech-to-Text)](https://glotlabs.ai/docs/realtime-asr/index.md): Stream audio and receive low-latency Speech-to-Text results over WebSocket. This endpoint is the recommended starting point for live transcription and automatically detects the spoken language.
- [Real-time Voice (Text-to-Speech)](https://glotlabs.ai/docs/realtime-tts/index.md): Glot Labs provides real-time Text-to-Speech over WebSocket for low-latency audio playback. Use this live endpoint when audio must begin streaming before the complete response is available. For single-request generation, 

## Batch

- [Batch Transcription (Speech-to-Text)](https://glotlabs.ai/docs/api/transcribe/index.md): Upload a complete audio file and receive a transcription in one batch request. Supports multiple languages via model selection. Optionally enables language correction and semantic tagging for enhanced output. For streami
- [Batch Text-to-Speech](https://glotlabs.ai/docs/api/speech/index.md): Generate spoken audio from text in a single synchronous request using Glot Labs voice aliases. For low-latency streaming playback, use Real-time Voice.

## Other & Add-ons

- [Live Translation](https://glotlabs.ai/docs/realtime-translate/index.md): Glot Labs provides a real-time speech-to-text **and translation** API via WebSocket — stream audio in one language and receive both the original transcript and a live translation into your target language.
- [Live Transcription + Translation](https://glotlabs.ai/docs/realtime-notetaker/index.md): This real-time workflow combines transcription, optional translation, always-on mishear correction, and optional speaker diarization for meetings and multi-speaker conversations. The endpoint path retains `/notetaker` fo
- [API Reference](https://glotlabs.ai/docs/api/index.md): The Glot Labs API provides AI-powered audio and text processing services. All endpoints are available at `https://api.glotlabs.ai`.
- [Translate text](https://glotlabs.ai/docs/api/translate/index.md): Translate text from a source language to a target language.
- [Annotate text](https://glotlabs.ai/docs/api/annotate/index.md): Annotate text with language corrections and semantic tags. Useful for processing colloquial transcriptions.
- [Clarify text](https://glotlabs.ai/docs/api/clarify/index.md): Transform noisy or colloquial transcriptions into clear, grammatically correct text.
- [Convert annotated text](https://glotlabs.ai/docs/api/convert/index.md): Convert annotated text (with semantic tags) into clean, readable text.
- [Format transcript](https://glotlabs.ai/docs/api/format/index.md): Transform a raw transcript into a structured document format such as meeting minutes, sales summaries, action items, subtitles, and more.
- [Analyze sentiment](https://glotlabs.ai/docs/api/sentiment/index.md): Analyze the overall sentiment and emotional tone of a transcript.
- [Analyze prosody](https://glotlabs.ai/docs/api/prosody/index.md): Analyze emotional expression from speech audio.
- [Voice security analysis](https://glotlabs.ai/docs/api/voice-security/index.md): Detect synthetic (deepfake) voices and verify liveness.
- [Generate speech fingerprint](https://glotlabs.ai/docs/api/fingerprint/index.md): Generate a speaker fingerprint embedding from an uploaded audio file.