> ## Documentation Index > Fetch the complete documentation index at: https://docs.slng.ai/llms.txt > Use this file to discover all available pages before exploring further. # Whisper Large v3 > Stream real-time transcripts from OpenAI Whisper Large v3 over WebSocket with VAD, partial results, and automatic language detection across 99 languages. ## AsyncAPI ````yaml api-reference/asyncapi/stt-slng.asyncapi.yaml /v1/stt/slng/openai/whisper:large-v3 id: /v1/stt/slng/openai/whisper:large-v3 title: Whisper Large v3 description: >- Stream real-time transcripts from OpenAI Whisper Large v3 over WebSocket with VAD, partial results, and automatic language detection across 99 languages. servers: - id: production protocol: wss host: api.slng.ai bindings: [] variables: [] - id: staging protocol: wss host: stageapi.slng.ai bindings: [] variables: [] address: /v1/stt/slng/openai/whisper:large-v3 parameters: [] bindings: - protocol: ws version: latest value: method: GET headers: type: object properties: X-World-Part-Override: type: string description: >- Target world part override. Auto-selected if not provided. Available world parts: `eu`. enum: - eu x-parser-schema-id: x-parser-schema-id: WebsocketHeadersSlngWhisper schemaProperties: - name: method type: string description: GET required: false - name: headers type: object required: false properties: - name: X-World-Part-Override type: string description: >- Target world part override. Auto-selected if not provided. Available world parts: `eu`. enumValues: - eu required: false operations: - &ref_1 id: sttWhisperLargeV3ReceiveInit title: Stt whisper large v3 receive init description: Initialize session on Whisper Large v3 type: receive messages: - &ref_9 id: SlngWhisperLargeV3SttInitRequest contentType: application/json payload: - name: Init Request description: Initialize an SLNG-hosted Whisper Large v3 STT session. type: object properties: - name: type type: string description: init required: true - name: config type: object description: >- Whisper recognition configuration options. Features like VAD, partial transcripts, and language detection are enabled by default and reported in the ready response. required: false properties: - name: language type: string description: ISO-639-1 language code. Auto-detected if not specified. enumValues: - af - am - ar - as - az - ba - be - bg - bn - bo - br - bs - ca - cs - cy - da - de - el - en - es - et - eu - fa - fi - fo - fr - gl - gu - ha - haw - he - hi - hr - ht - hu - hy - id - is - it - ja - jw - ka - kk - km - kn - ko - la - lb - ln - lo - lt - lv - mg - mi - mk - ml - mn - mr - ms - mt - my - ne - nl - nn - 'no' - oc - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - sn - so - sq - sr - su - sv - sw - ta - te - tg - th - tk - tl - tr - tt - uk - ur - uz - vi - yi - yo - zh - yue required: false - name: sample_rate type: integer description: Input audio sample rate in Hz. required: false - name: encoding type: string description: Input audio encoding format. enumValues: - linear16 - mp3 - opus required: false headers: [] jsonPayloadSchema: type: object description: >- Initialize a Whisper STT session with recognition configuration before streaming audio. required: - type properties: type: type: string const: init x-parser-schema-id: config: type: object description: >- Whisper recognition configuration options. Features like VAD, partial transcripts, and language detection are enabled by default and reported in the ready response. properties: language: type: string description: ISO-639-1 language code. Auto-detected if not specified. example: en enum: - af - am - ar - as - az - ba - be - bg - bn - bo - br - bs - ca - cs - cy - da - de - el - en - es - et - eu - fa - fi - fo - fr - gl - gu - ha - haw - he - hi - hr - ht - hu - hy - id - is - it - ja - jw - ka - kk - km - kn - ko - la - lb - ln - lo - lt - lv - mg - mi - mk - ml - mn - mr - ms - mt - my - ne - nl - nn - 'no' - oc - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - sn - so - sq - sr - su - sv - sw - ta - te - tg - th - tk - tl - tr - tt - uk - ur - uz - vi - yi - yo - zh - yue x-parser-schema-id: WhisperLanguageCode sample_rate: type: integer description: Input audio sample rate in Hz. default: 16000 x-parser-schema-id: encoding: type: string description: Input audio encoding format. default: linear16 enum: - linear16 - mp3 - opus x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: SlngWhisperSttInitPayload title: Init Request description: Initialize an SLNG-hosted Whisper Large v3 STT session. example: |- { "type": "init", "config": { "language": "en", "sample_rate": 16000, "encoding": "linear16" } } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngWhisperLargeV3SttInitRequest bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: /v1/stt/slng/openai/whisper:large-v3 - &ref_2 id: sttWhisperLargeV3ReceiveAudio title: Stt whisper large v3 receive audio description: Send audio frame to Whisper Large v3 type: receive messages: - &ref_10 id: SttAudioMessage contentType: application/json payload: - name: Audio Message description: Stream an audio frame to be transcribed. type: object properties: - name: type type: string description: audio required: true - name: data type: string description: Base64-encoded audio data required: true headers: [] jsonPayloadSchema: type: object description: Stream an audio frame to be transcribed. required: - type - data properties: type: type: string const: audio x-parser-schema-id: data: type: string format: byte description: Base64-encoded audio data x-parser-schema-id: x-parser-schema-id: title: Audio Message description: Stream an audio frame to be transcribed. example: |- { "type": "audio", "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEA..." } bindings: [] extensions: - id: x-parser-unique-object-id value: SttAudioMessage bindings: [] extensions: *ref_0 - &ref_3 id: sttWhisperLargeV3ReceiveFinalize title: Stt whisper large v3 receive finalize description: Force-finalize buffered audio on Whisper Large v3 type: receive messages: - &ref_11 id: SttFinalizeMessage contentType: application/json payload: - name: Finalize Message description: >- Force-finalize buffered audio tokens without closing the connection. type: object properties: - name: type type: string description: finalize required: true headers: [] jsonPayloadSchema: type: object description: >- Mid-stream flush — forces the server to finalize any buffered audio and return results. The connection remains open for further audio. required: - type properties: type: type: string const: finalize x-parser-schema-id: x-parser-schema-id: title: Finalize Message description: Force-finalize buffered audio tokens without closing the connection. example: |- { "type": "finalize" } bindings: [] extensions: - id: x-parser-unique-object-id value: SttFinalizeMessage bindings: [] extensions: *ref_0 - &ref_4 id: sttWhisperLargeV3ReceiveClose title: Stt whisper large v3 receive close description: Close audio stream on Whisper Large v3 type: receive messages: - &ref_12 id: SttCloseMessage contentType: application/json payload: - name: Close Message description: Signal end of audio stream and close the connection. type: object properties: - name: type type: string description: close required: true headers: [] jsonPayloadSchema: type: object description: >- Signal that no more audio will be sent. The server processes remaining audio, sends final results, then closes the connection. required: - type properties: type: type: string const: close x-parser-schema-id: x-parser-schema-id: title: Close Message description: Signal end of audio stream and close the connection. example: |- { "type": "close" } bindings: [] extensions: - id: x-parser-unique-object-id value: SttCloseMessage bindings: [] extensions: *ref_0 - &ref_5 id: sttWhisperLargeV3SendReady title: Stt whisper large v3 send ready description: Receive ready signal from Whisper Large v3 type: send messages: - &ref_13 id: SlngWhisperSttReadyResponse contentType: application/json payload: - name: Ready Response description: Indicates the Whisper session is ready to receive audio. type: object properties: - name: type type: string description: ready required: true - name: session_id type: string description: Unique session identifier. required: true - name: context_id type: string description: >- Context identifier for correlating messages within this session. required: false - name: model type: string description: Model identifier used for this session. required: false - name: commands type: array description: Supported control commands for this session. required: false properties: - name: item type: string required: false - name: features type: object description: Capabilities enabled for this session. required: false properties: - name: vad type: boolean description: Voice Activity Detection enabled. required: false - name: partial_transcripts type: boolean description: Partial transcript streaming enabled. required: false - name: final_transcripts type: boolean description: Final transcript delivery enabled. required: false - name: language_detection type: boolean description: Automatic language detection enabled. required: false - name: speaker_diarization type: boolean description: >- Reported by the model but not currently functional. Speaker labels are not included in transcript payloads. required: false headers: [] jsonPayloadSchema: type: object description: >- Indicates the Whisper session is initialized and ready to receive audio. Includes model info, supported commands, and enabled features. required: - type - session_id properties: type: type: string const: ready x-parser-schema-id: session_id: type: string description: Unique session identifier. x-parser-schema-id: context_id: type: string description: Context identifier for correlating messages within this session. x-parser-schema-id: model: type: string description: Model identifier used for this session. example: whisper-large-v3 x-parser-schema-id: commands: type: array description: Supported control commands for this session. items: type: string x-parser-schema-id: example: - flush - stop - clear - context x-parser-schema-id: features: type: object description: Capabilities enabled for this session. properties: vad: type: boolean description: Voice Activity Detection enabled. x-parser-schema-id: partial_transcripts: type: boolean description: Partial transcript streaming enabled. x-parser-schema-id: final_transcripts: type: boolean description: Final transcript delivery enabled. x-parser-schema-id: language_detection: type: boolean description: Automatic language detection enabled. x-parser-schema-id: speaker_diarization: type: boolean description: >- Reported by the model but not currently functional. Speaker labels are not included in transcript payloads. x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: title: Ready Response description: Indicates the Whisper session is ready to receive audio. example: |- { "type": "ready", "session_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890", "context_id": "stt-a1b2c3d4-e5f6-7890-abcd-ef1234567890", "model": "whisper-large-v3", "commands": [ "flush", "stop", "clear", "context" ], "features": { "vad": true, "partial_transcripts": true, "final_transcripts": true, "language_detection": true, "speaker_diarization": true } } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngWhisperSttReadyResponse bindings: [] extensions: *ref_0 - &ref_6 id: sttWhisperLargeV3SendPartialTranscript title: Stt whisper large v3 send partial transcript description: Receive partial transcript from Whisper Large v3 type: send messages: - &ref_14 id: SlngWhisperSttPartialTranscript contentType: application/json payload: - name: Partial Transcript description: >- Interim Whisper transcription result, updated as more audio is processed. type: object properties: - name: type type: string description: partial_transcript required: true - name: transcript type: string description: >- Interim transcription text, updated as more audio is processed. required: true - name: confidence type: number description: Confidence score (0-1). required: false - name: language type: string description: Detected language code. required: false - name: context_id type: string description: Context identifier for correlating messages. required: false - name: session_id type: string description: Session identifier. required: false - name: is_final type: boolean description: Always false for partial transcripts. required: false - name: audio_duration type: number description: Duration of audio processed so far, in seconds. required: false headers: [] jsonPayloadSchema: type: object description: >- Interim transcription result from Whisper. Sent progressively as audio is processed, allowing real-time display of in-progress transcription. required: - type - transcript properties: type: type: string const: partial_transcript x-parser-schema-id: transcript: type: string description: Interim transcription text, updated as more audio is processed. x-parser-schema-id: confidence: type: number minimum: 0 maximum: 1 description: Confidence score (0-1). x-parser-schema-id: language: type: string description: Detected language code. x-parser-schema-id: context_id: type: string description: Context identifier for correlating messages. x-parser-schema-id: session_id: type: string description: Session identifier. x-parser-schema-id: is_final: type: boolean description: Always false for partial transcripts. x-parser-schema-id: audio_duration: type: number description: Duration of audio processed so far, in seconds. x-parser-schema-id: x-parser-schema-id: title: Partial Transcript description: >- Interim Whisper transcription result, updated as more audio is processed. example: |- { "type": "partial_transcript", "context_id": "stt-a1b2c3d4-e5f6-7890-abcd-ef1234567890", "session_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890", "transcript": "The quick brown fox jumps over the", "language": "en", "confidence": 1, "is_final": false, "audio_duration": 2.56 } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngWhisperSttPartialTranscript bindings: [] extensions: *ref_0 - &ref_7 id: sttWhisperLargeV3SendFinalTranscript title: Stt whisper large v3 send final transcript description: Receive final transcript from Whisper Large v3 type: send messages: - &ref_15 id: SlngWhisperSttFinalTranscript contentType: application/json payload: - name: Final Transcript description: Final Whisper transcription result with segment-level detail. type: object properties: - name: type type: string description: final_transcript required: true - name: transcript type: string description: Final transcription text. required: true - name: confidence type: number description: Confidence score (0-1). required: false - name: language type: string description: Detected language code. required: false - name: context_id type: string description: Context identifier for correlating messages. required: false - name: session_id type: string description: Session identifier. required: false - name: is_final type: boolean description: Always true for final transcripts. required: false - name: audio_duration type: number description: Total duration of audio processed, in seconds. required: false - name: segments type: array description: >- Whisper segment-level detail with timing and log probabilities. required: false properties: - name: text type: string description: Transcribed text for this segment. required: false - name: start type: number description: Segment start time in seconds. required: false - name: end type: number description: Segment end time in seconds. required: false - name: avg_logprob type: number description: >- Average log probability for this segment (higher = more confident). required: false headers: [] jsonPayloadSchema: type: object description: >- Final transcription result from Whisper. Includes the complete transcript, segment-level timing with log probabilities, and total audio duration. required: - type - transcript properties: type: type: string const: final_transcript x-parser-schema-id: transcript: type: string description: Final transcription text. x-parser-schema-id: confidence: type: number minimum: 0 maximum: 1 description: Confidence score (0-1). x-parser-schema-id: language: type: string description: Detected language code. x-parser-schema-id: context_id: type: string description: Context identifier for correlating messages. x-parser-schema-id: session_id: type: string description: Session identifier. x-parser-schema-id: is_final: type: boolean description: Always true for final transcripts. x-parser-schema-id: audio_duration: type: number description: Total duration of audio processed, in seconds. x-parser-schema-id: segments: type: array description: Whisper segment-level detail with timing and log probabilities. items: type: object properties: text: type: string description: Transcribed text for this segment. x-parser-schema-id: start: type: number description: Segment start time in seconds. x-parser-schema-id: end: type: number description: Segment end time in seconds. x-parser-schema-id: avg_logprob: type: number description: >- Average log probability for this segment (higher = more confident). x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: title: Final Transcript description: Final Whisper transcription result with segment-level detail. example: |- { "type": "final_transcript", "context_id": "stt-a1b2c3d4-e5f6-7890-abcd-ef1234567890", "session_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890", "transcript": "The quick brown fox jumps over the lazy dog.", "language": "en", "confidence": 1, "is_final": true, "audio_duration": 3.84, "segments": [ { "text": " The quick brown fox jumps over the lazy dog.", "start": 0.066, "end": 3.71, "avg_logprob": -0.08 } ] } bindings: [] extensions: - id: x-parser-unique-object-id value: SlngWhisperSttFinalTranscript bindings: [] extensions: *ref_0 - &ref_8 id: sttWhisperLargeV3SendError title: Stt whisper large v3 send error description: Receive error from Whisper Large v3 type: send messages: - &ref_16 id: SttErrorResponse contentType: application/json payload: - name: Error Response description: Indicates an error occurred during recognition. type: object properties: - name: type type: string description: error required: true - name: code type: string description: >- Error code (e.g., auth_error, config_error, rate_limit, provider_error) required: true - name: message type: string description: Human-readable error description required: true headers: [] jsonPayloadSchema: type: object description: Indicates an error occurred during recognition. required: - type - code - message properties: type: type: string const: error x-parser-schema-id: code: type: string description: >- Error code (e.g., auth_error, config_error, rate_limit, provider_error) x-parser-schema-id: message: type: string description: Human-readable error description x-parser-schema-id: x-parser-schema-id: title: Error Response description: Indicates an error occurred during recognition. example: |- { "type": "error", "code": "auth_error", "message": "Invalid or expired API key" } bindings: [] extensions: - id: x-parser-unique-object-id value: SttErrorResponse bindings: [] extensions: *ref_0 sendOperations: - *ref_1 - *ref_2 - *ref_3 - *ref_4 receiveOperations: - *ref_5 - *ref_6 - *ref_7 - *ref_8 sendMessages: - *ref_9 - *ref_10 - *ref_11 - *ref_12 receiveMessages: - *ref_13 - *ref_14 - *ref_15 - *ref_16 extensions: - id: x-parser-unique-object-id value: /v1/stt/slng/openai/whisper:large-v3 securitySchemes: - id: bearer name: bearer type: http description: > API key issued by SLNG. Pass as `Authorization: Bearer ` in the WebSocket upgrade request headers. scheme: bearer extensions: [] ````