> ## Documentation Index > Fetch the complete documentation index at: https://docs.munsit.com/llms.txt > Use this file to discover all available pages before exploring further. # Speech-to-Text Streaming ## Endpoint `WS /websocket/speech-to-text` ## Authentication The server accepts either: | Field | Type | Required | Description | | --------------- | ------ | -------- | --------------------------------------- | | `x-api-key` | string | No | API key in header or query | | `Authorization` | string | No | Bearer token header | | `token` | string | No | Token query param fallback for browsers | At least one auth method is required. If auth is invalid, the connection is rejected or closed. ## Query Parameters | Field | Type | Required | Description | | ------- | ------ | -------- | ------------------------------------------------------------------------------------------------- | | `model` | string | No | ASR model to use: `munsit` (default) or `munsit-en-ar` (mixed Arabic-English with code-switching) | ### Connection example ```text theme={null} wss://api.munsit.com/api/v1/websocket/speech-to-text?x-api-key=YOUR_MUNSIT_API_KEY&model=munsit ``` ## Supported audio input * First chunk must be WAV (with headers) * Subsequent chunks can be WAV or raw PCM ## Client message format Primary format (`event` + `data`): ```json theme={null} { "event": "audio_chunk", "data": { "audioBuffer": [1, 2, 3] } } ``` Compatibility format also accepted: ```json theme={null} { "audioBuffer": [1, 2, 3] } ``` `audioBuffer` must be an array of byte values (`0-255`). ## Events to emit ### `audio_chunk` * **Direction**: client -> server * **Payload**: `audioBuffer` as `Array` * **Guidance**: * send approximately every \~1 second * first chunk should include full WAV headers * after first chunk, PCM chunks are accepted ## Events to listen to ### `transcription` * **Direction**: server -> client * **Type**: `string` * **Meaning**: cumulative Arabic transcript generated from all received chunks ### `transcription_error` * **Direction**: server -> client * **Type**: `string` * **Meaning**: error details during streaming transcription ### Connection/auth notes * **`connect`**: client-level WebSocket open event (successful handshake) * **`authentication_error`**: not emitted as a dedicated WS event in current backend; invalid auth is handled by rejecting/closing the connection ## Recommended flow 1. Connect to `WS /websocket/speech-to-text` with auth 2. Confirm the socket is open on the client side 3. Emit `audio_chunk` payloads (roughly every \~1s) 4. Listen for `transcription_error` and handle failures 5. Listen for `transcription` and render live text updates 6. Safely disconnect when transcription is complete ## AsyncAPI ````yaml api-reference/asyncapi.json speech-to-text id: speech-to-text title: Speech-to-text description: '' servers: - id: production protocol: wss host: api.munsit.com bindings: [] variables: [] address: wss://api.munsit.com/api/v1/websocket/speech-to-text parameters: [] bindings: - protocol: ws version: latest value: headers: type: object properties: x-api-key: type: string description: API key header Authorization: type: string description: Bearer token header query: type: object properties: x-api-key: type: string description: Your Munsit API key token: type: string description: Optional auth token for browser WebSocket fallback schemaProperties: - name: headers type: object required: false properties: - name: x-api-key type: string description: API key header required: false - name: Authorization type: string description: Bearer token header required: false - name: query type: object required: false properties: - name: x-api-key type: string description: Your Munsit API key required: false - name: token type: string description: Optional auth token for browser WebSocket fallback required: false operations: - &ref_3 id: sendSttAudioChunk title: Send stt audio chunk type: send messages: - &ref_6 id: audio_chunk payload: - oneOf: &ref_0 - type: object required: - event - data properties: event: type: string const: audio_chunk x-parser-schema-id: data: type: object required: - audioBuffer properties: audioBuffer: type: array items: type: integer minimum: 0 maximum: 255 x-parser-schema-id: description: >- Audio bytes as Uint8 values. First chunk should be WAV. x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: - type: object required: - audioBuffer properties: audioBuffer: type: array items: type: integer minimum: 0 maximum: 255 x-parser-schema-id: description: Compatibility format accepted by server. x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: name: Audio Chunk description: Send a chunk of audio bytes for transcription headers: [] jsonPayloadSchema: oneOf: *ref_0 x-parser-schema-id: title: Audio Chunk description: Send a chunk of audio bytes for transcription example: '{}' bindings: [] extensions: - id: x-parser-unique-object-id value: audio_chunk bindings: [] extensions: &ref_1 - id: x-parser-unique-object-id value: speech-to-text - &ref_2 id: receiveSttEvents title: Receive stt events type: receive messages: - &ref_4 id: transcription payload: - name: Transcription description: Transcription text event from server type: object properties: - name: event type: string description: transcription required: true - name: data type: string description: Cumulative transcription text required: true headers: [] jsonPayloadSchema: type: object required: - event - data properties: event: type: string const: transcription x-parser-schema-id: data: type: string description: Cumulative transcription text x-parser-schema-id: x-parser-schema-id: title: Transcription description: Transcription text event from server example: |- { "event": "", "data": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: transcription - &ref_5 id: transcription_error payload: - name: Transcription Error description: Error event from server type: object properties: - name: event type: string description: transcription_error required: true - name: data type: string description: Error message required: true headers: [] jsonPayloadSchema: type: object required: - event - data properties: event: type: string const: transcription_error x-parser-schema-id: data: type: string description: Error message x-parser-schema-id: x-parser-schema-id: title: Transcription Error description: Error event from server example: |- { "event": "", "data": "" } bindings: [] extensions: - id: x-parser-unique-object-id value: transcription_error bindings: [] extensions: *ref_1 sendOperations: - *ref_2 receiveOperations: - *ref_3 sendMessages: - *ref_4 - *ref_5 receiveMessages: - *ref_6 extensions: - id: x-parser-unique-object-id value: speech-to-text securitySchemes: [] ````