# Introduction

> Munsit is the Arabic voice API. One key gets you natural Arabic speech, the most accurate Arabic speech recognition available, and everything in between. Here's the first call.

## Your first call

Try it live — type Arabic and hear it, or drop in audio and read it. Flip the switch in the corner for the exact call, then paste your key and run it.

```
curl -X POST "https://api.munsit.com/api/v1/text-to-speech/faseeh-v1-preview" \
  -H "x-api-key: $MUNSIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"voice_id":"...","text":"مرحبا بك في منصت"}' \
  --output speech.wav
```

```
curl -X POST "https://api.munsit.com/api/v1/audio/transcribe" \
  -H "x-api-key: $MUNSIT_API_KEY" \
  -F "file=@meeting.mp3"
```

```
wscat -c "wss://api.munsit.com/api/v1/websocket/speech-to-text" \
  -H "x-api-key: $MUNSIT_API_KEY"

# send audio chunks, read transcripts back
```

```
curl -X POST "https://api.munsit.com/api/v1/voices/clone" \
  -H "x-api-key: $MUNSIT_API_KEY" \
  -F "file=@sample.mp3" \
  -F "name=Layla"
```

Response

```
// audio bytes — save and play
```

Response

```
{
  "statusCode": 200,
  "data": {
    "transcriptionId": "805059bf-7c3f-4a1e-9d2b-1f0c6ae83b47",
    "transcription": "اجتماع الفريق يبدأ الساعة العاشرة"
  },
  "message": "Success"
}
```

Response

```
// transcripts arrive as the speaker talks
{ "type": "transcript", "transcription": "اجتماع الفريق يبدأ الساعة العاشرة" }
```

Response

```
{ "voice_id": "cl-layla-8f21", "status": "ready" }
```

Need a key? Create one in the dashboard — free credits on signup, no card. [Get an API key →](https://app.munsit.com/en/api-keys)

## The whole surface

Every endpoint and agent plugin, all behind that one key. Nothing here is a separate signup.

[

### Text to Speech

→](/text-to-speech/get-started)

faseeh · natural Arabic voices

-   [Synthesize /text-to-speech/{model}](/text-to-speech/synthesize)
-   [Stream audio out /websocket/text-to-speech](/text-to-speech/audio-streaming-output)
-   [List voices /voices](/text-to-speech/voices)
-   [Preview a voice /voices/preview](/text-to-speech/voice-preview)
-   [Clone a voice /voices/clone](/text-to-speech/voice-cloning)
-   [Tashkīl — diacritize /tashkil/diacritize](/text-to-speech/tashkil)

[

### Speech to Text

→](/speech-to-text/get-started)

munsit · #1 on Arabic ASR

-   [Transcribe /audio/transcribe](/speech-to-text/transcribe)
-   [Streaming /websocket/speech-to-text](/speech-to-text/streaming)
-   [Speaker diarization /audio/diarization/transcribe](/speech-to-text/diarization)
-   [Diarization + sentiment /diarization/{id}/sentiment-analysis](/speech-to-text/diarization-sentiment)
-   [Minutes of a meeting /minutes-of-meeting/transcribe](/speech-to-text/minutes-of-meetings)

[

### Understanding

→](/understanding/sentiment-analysis)

on top of any transcript

-   [Sentiment analysis /audio/{id}/sentiment-analysis](/understanding/sentiment-analysis)
-   [Keyword extraction /minutes-of-meeting/{id}/keyword-extraction](/understanding/keyword-extraction)
-   [Translation /translation/stream](/understanding/translation)

[

### Audio

→](/audio/voice-isolation)

clean it before you use it

-   [Voice isolation /denoise](/audio/voice-isolation)
-   [Job status /denoise/{id}/progress](/audio/denoise-progress)
-   [List models /models](/text-to-speech/models)

[

### Voice agents

→](/integrations/livekit)

drop-in plugins

-   [LiveKit STT + TTS plugin](/integrations/livekit)
-   [Pipecat plugin](/integrations/pipecat)
-   [VAPI guide](/integrations/vapi)
-   [Ultravox guide](/integrations/ultravox)

[

### Getting started

→](/quickstart)

before you build

-   [Quickstart guide](/quickstart)
-   [Authentication guide](/authentication)
-   [Rate limits guide](/rate-limits)
-   [Errors guide](/errors)
-   [Support guide](/support)

## Pick your path

Four common jobs. Each one is a guide that ends with working code.

[Generate Arabic speech Natural voices across Gulf dialects, plus MSA. faseeh · /text-to-speech](/text-to-speech/get-started) [Transcribe Arabic audio Files or live. 25+ dialects, no dialect parameter needed. munsit · /audio/transcribe](/speech-to-text/get-started) [Stream in real time Two WebSockets — synthesize as text arrives, or transcribe as they speak. wss · /websocket/\*](/text-to-speech/audio-streaming-output) [Build a voice agent Drop-in plugins for LiveKit, Pipecat, VAPI and Ultravox. 5 integrations](/integrations/livekit)

## Running it yourself

If you can't send audio to a cloud, you don't have to.

**On-premises deployment.** Run Munsit entirely inside your own data centre or private environment. [Self hosting →](/deployment/self-hosting)[Data privacy →](/deployment/compliance)

## Build with an AI assistant

These docs are also an MCP server, so your assistant can read them itself instead of you pasting pages into a chat window.

```
claude mcp add --transport http munsit-docs https://docs.munsit.com/api/mcp
```

**Five tools:** search the docs, read a page, list every page, list every endpoint, and pull one endpoint's full schema. No key, no auth, nothing to install. [Docs MCP server →](/mcp)[Munsit MCP server →](/mcp-server)[llms-full.txt →](/llms-full.txt)