# Munsit Documentation

## Docs

- [Authentication](https://docs.munsit.com/api-reference/authentication.md)
- [Denoise](https://docs.munsit.com/api-reference/denoise.md): Remove background noise and isolate voice from audio files. Upload an audio file and receive a cleaned audio file with enhanced voice clarity.
- [Diarization](https://docs.munsit.com/api-reference/diarization.md): Upload audio and receive diarization segments merged with transcription.
- [Endpoints](https://docs.munsit.com/api-reference/endpoints.md)
- [Errors](https://docs.munsit.com/api-reference/errors.md)
- [Minutes of Meeting Transcriber](https://docs.munsit.com/api-reference/minutes-of-meeting-transcriber.md): Upload meeting audio and receive structured transcription output.
- [Get Models](https://docs.munsit.com/api-reference/models.md): Retrieve a list of all available voice synthesis models
- [Quickstart](https://docs.munsit.com/api-reference/quickstart.md)
- [API Rate Limits](https://docs.munsit.com/api-reference/rate-limits.md)
- [Diarization Sentiment Analysis](https://docs.munsit.com/api-reference/stt-diarization-sentiment-analysis.md): Generate sentiment analysis from a diarization record ID.
- [Keyword Extraction](https://docs.munsit.com/api-reference/stt-keyword-extraction.md): Extract keywords and topic insights from a meeting transcription.
- [Sentiment Analysis](https://docs.munsit.com/api-reference/stt-sentiment-analysis.md): Generate sentiment analysis from an audio transcription ID.
- [Speech-to-Text Streaming](https://docs.munsit.com/api-reference/stt-streaming.md)
- [Translation](https://docs.munsit.com/api-reference/stt-translation.md): Translate text with Server-Sent Events (SSE) streaming response.
- [Text-to-Speech](https://docs.munsit.com/api-reference/text-to-speech-post.md): Generate speech from Arabic text using a specific model. Supports both streaming and non-streaming responses.
- [Text-to-Speech Stream](https://docs.munsit.com/api-reference/text-to-speech-stream.md): Generate speech from Arabic text using a specific model. Supports both streaming and non-streaming responses.
- [Transcriber](https://docs.munsit.com/api-reference/transcriber.md): Upload a pre-recorded audio file and receive Arabic transcription with timestamps.
- [Voice Clone](https://docs.munsit.com/api-reference/voice-clone.md): Create a cloned voice from an audio file. This endpoint allows you to create a new voice by providing a voice sample and reference audio.
- [Voice Preview](https://docs.munsit.com/api-reference/voice-preview.md): Generate a preview of a voice you want to clone. This API allows you to test how a voice will sound before creating it as a permanent voice.
- [Get Voices](https://docs.munsit.com/api-reference/voices.md): Retrieve a list of all available voices for text-to-speech synthesis
- [Text-To-Speech WebSocket](https://docs.munsit.com/api-reference/websocket.md)
- [Audio Narrative](https://docs.munsit.com/capabilities/audio-narrative.md): Turn any text into a fully hosted, embeddable audio experience
- [Keyword Extraction](https://docs.munsit.com/capabilities/keyword-extraction.md): Extract important terms, entities, and themes from meeting transcripts
- [Sentiment Analysis](https://docs.munsit.com/capabilities/sentiment-analysis.md): Analyze tone, emotions, and sentiment trends from transcribed audio
- [Translation](https://docs.munsit.com/capabilities/translation.md): Translate text between languages with real-time streaming output
- [Voice Cloning](https://docs.munsit.com/capabilities/voice-cloning.md): Clone and design custom Arabic voices
- [Voice Isolation](https://docs.munsit.com/capabilities/voice-isolation.md): Isolate voices from background noise
- [Self Hosting](https://docs.munsit.com/docs/capabilities/on.md)
- [Data Privacy Compliance](https://docs.munsit.com/docs/getting-started/complaince.md)
- [Support](https://docs.munsit.com/docs/getting-started/support.md)
- [Introduction](https://docs.munsit.com/index.md): Munsit - First True Arabic Voice AI that speaks Dialects From Abu Dhabi to Rabat with Voice Cloning & On-prem support
- [LiveKit Plugin](https://docs.munsit.com/integrations/livekit-plugin.md): Integrate Munsit Arabic TTS with LiveKit voice agents
- [LiveKit STT Plugin](https://docs.munsit.com/integrations/livekit-stt-plugin.md): Use Munsit speech-to-text with LiveKit Agents
- [Pipecat Plugin](https://docs.munsit.com/integrations/pipecat-plugin.md): Build conversational Arabic AI agents with Pipecat and Munsit TTS
- [Ultravox Integration](https://docs.munsit.com/integrations/ultravox-integration.md): Add a Custom FASEEH Voice to UltraVox
- [VAPI Integration](https://docs.munsit.com/integrations/vapi-integration.md): Integrate Munsit Arabic TTS with VAPI voice assistants
- [Models](https://docs.munsit.com/models.md): Explore Munsit's voice synthesis models
- [Diarization](https://docs.munsit.com/speech-to-text/diarization.md): Identify speakers and merge diarization with transcription output
- [Get Started](https://docs.munsit.com/speech-to-text/get-started.md)
- [Minutes of Meetings](https://docs.munsit.com/speech-to-text/minutes-of-meetings.md): Transcribe and structure Arabic meeting recordings for downstream analysis
- [Transcriber](https://docs.munsit.com/speech-to-text/transcriber.md): Upload Arabic audio files and receive high-accuracy transcription output
- [Audio Streaming Output](https://docs.munsit.com/text-to-speech/audio-streaming-output.md)
- [Get Started](https://docs.munsit.com/text-to-speech/get-started.md)
- [Voices](https://docs.munsit.com/text-to-speech/voices.md)

## OpenAPI Specs

- [openapi](https://docs.munsit.com/api-reference/openapi.json)

## AsyncAPI Specs

- [asyncapi](https://docs.munsit.com/api-reference/asyncapi.json)

## Optional

- [Dashboard](https://app.munsit.com/)
- [Support](https://calendar.google.com/calendar/u/0/appointments/schedules/AcZssZ1fgxJD82YNieOXrhWQ1_SfuJLthGBx7YDy3AQhdtdS7brN5Y3ZH_OKHkeIwhBTnmTZqkKjSQVI)