> ## 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. # Speechmatics Realtime v2 > Real-time speech-to-text transcription with Speechmatics over WebSocket. Stream binary audio and receive partial and final transcripts with word timing, confidence, and optional diarization. ## AsyncAPI ````yaml api-reference/asyncapi/stt-speechmatics.asyncapi.yaml /v1/stt/speechmatics/realtime:v2 id: /v1/stt/speechmatics/realtime:v2 title: Speechmatics Realtime v2 description: >- Real-time speech-to-text transcription with Speechmatics over WebSocket. Stream binary audio and receive partial and final transcripts with word timing, confidence, and optional diarization. servers: - id: production protocol: wss host: api.slng.ai bindings: [] variables: [] - id: staging protocol: wss host: stageapi.slng.ai bindings: [] variables: [] address: /v1/stt/speechmatics/realtime:v2 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: `ap`, `eu`. enum: - ap - eu x-parser-schema-id: x-parser-schema-id: WebsocketHeadersSpeechmatics 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: `ap`, `eu`. enumValues: - ap - eu required: false operations: - &ref_1 id: sttSpeechmaticsRealtimeV2ReceiveInit title: Stt speechmatics realtime v2 receive init description: Initialize session on Speechmatics Realtime v2 type: receive messages: - &ref_9 id: SpeechmaticsRealtimeInitRequest contentType: application/json payload: - name: Init Request (Speechmatics) description: >- Initialize a Speechmatics Realtime session with recognition configuration. type: object properties: - name: type type: string description: init required: true - name: config type: object description: Speechmatics recognition configuration options. required: false properties: - name: language type: string description: ISO language code for transcription. required: false - name: encoding type: string description: Raw audio encoding for binary frames. enumValues: - pcm_s16le - pcm_f32le - mulaw - linear16 required: false - name: sample_rate type: integer description: Audio sample rate in Hz. required: false - name: operating_point type: string description: Quality level. enumValues: - standard - enhanced required: false - name: domain type: string description: Specialized transcription domain. required: false - name: output_locale type: string description: Locale for formatted output. required: false - name: additional_vocab type: array description: >- Custom vocabulary entries. Each entry is either a string, or an object of the form `{ content, sounds_like }`. required: false properties: - name: item type: string required: false - name: diarization type: string description: Diarization mode. enumValues: - none - speaker - channel - channel_and_speaker required: false - name: max_delay type: number description: Maximum final transcript delay in seconds. required: false - name: max_delay_mode type: string description: >- Whether max_delay is enforced flexibly or as a fixed bound. enumValues: - flexible - fixed required: false - name: enable_partials type: boolean description: Enable partial transcript messages. required: false - name: enable_entities type: boolean description: Enable entity detection. required: false - name: punctuation_overrides type: object description: Punctuation settings. required: false properties: - name: sensitivity type: number required: false - name: permitted_marks type: array required: false properties: - name: item type: string required: false - name: speaker_diarization_config type: object description: Speaker diarization settings. required: false properties: - name: max_speakers type: integer required: false - name: prefer_current_speaker type: boolean required: false - name: speaker_sensitivity type: number required: false - name: remove_disfluencies type: boolean description: Remove disfluencies from transcripts. required: false - name: channel_diarization_labels type: array description: Channel labels for channel diarization. required: false properties: - name: item type: string required: false - name: volume_threshold type: number description: Lower volume limit for audio filtering. required: false - name: end_of_utterance_silence_trigger type: number description: >- Silence duration in seconds before emitting an end-of-utterance signal. Zero disables it. required: false headers: [] jsonPayloadSchema: type: object description: >- Initialize a Speechmatics Realtime session. Must be the first message, before streaming audio. required: - type properties: type: type: string const: init x-parser-schema-id: config: type: object description: Speechmatics recognition configuration options. properties: language: type: string description: ISO language code for transcription. default: en x-parser-schema-id: encoding: type: string description: Raw audio encoding for binary frames. enum: - pcm_s16le - pcm_f32le - mulaw - linear16 default: pcm_s16le x-parser-schema-id: sample_rate: type: integer description: Audio sample rate in Hz. default: 16000 x-parser-schema-id: operating_point: type: string description: Quality level. enum: - standard - enhanced default: standard x-parser-schema-id: domain: type: string description: Specialized transcription domain. x-parser-schema-id: output_locale: type: string description: Locale for formatted output. x-parser-schema-id: additional_vocab: type: array description: >- Custom vocabulary entries. Each entry is either a string, or an object of the form `{ content, sounds_like }`. items: type: string x-parser-schema-id: x-parser-schema-id: diarization: type: string description: Diarization mode. enum: - none - speaker - channel - channel_and_speaker default: none x-parser-schema-id: max_delay: type: number description: Maximum final transcript delay in seconds. minimum: 0.7 maximum: 4 default: 4 x-parser-schema-id: max_delay_mode: type: string description: Whether max_delay is enforced flexibly or as a fixed bound. enum: - flexible - fixed default: flexible x-parser-schema-id: enable_partials: type: boolean description: Enable partial transcript messages. default: false x-parser-schema-id: enable_entities: type: boolean description: Enable entity detection. default: false x-parser-schema-id: punctuation_overrides: type: object description: Punctuation settings. properties: sensitivity: type: number minimum: 0 maximum: 1 x-parser-schema-id: permitted_marks: type: array items: type: string x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: speaker_diarization_config: type: object description: Speaker diarization settings. properties: max_speakers: type: integer minimum: 2 x-parser-schema-id: prefer_current_speaker: type: boolean x-parser-schema-id: speaker_sensitivity: type: number minimum: 0 maximum: 1 x-parser-schema-id: x-parser-schema-id: remove_disfluencies: type: boolean description: Remove disfluencies from transcripts. default: false x-parser-schema-id: channel_diarization_labels: type: array description: Channel labels for channel diarization. items: type: string x-parser-schema-id: x-parser-schema-id: volume_threshold: type: number description: Lower volume limit for audio filtering. minimum: 0 x-parser-schema-id: end_of_utterance_silence_trigger: type: number description: >- Silence duration in seconds before emitting an end-of-utterance signal. Zero disables it. minimum: 0 x-parser-schema-id: x-parser-schema-id: SpeechmaticsRealtimeConfig x-parser-schema-id: title: Init Request (Speechmatics) description: >- Initialize a Speechmatics Realtime session with recognition configuration. example: |- { "type": "init", "config": { "language": "en", "encoding": "pcm_s16le", "sample_rate": 16000, "operating_point": "enhanced", "enable_partials": true } } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeInitRequest bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: /v1/stt/speechmatics/realtime:v2 - &ref_2 id: sttSpeechmaticsRealtimeV2ReceiveAudio title: Stt speechmatics realtime v2 receive audio description: Send audio frame to Speechmatics Realtime v2 type: receive messages: - &ref_10 id: SpeechmaticsRealtimeBinaryAudio contentType: application/octet-stream payload: - type: string format: binary description: Stream a raw binary audio frame to be transcribed. x-parser-schema-id: name: Binary Audio Frame headers: [] jsonPayloadSchema: type: string format: binary description: >- Raw binary audio data in the encoding declared at init (default linear16 PCM at 16kHz). Sent as a binary WebSocket frame — no JSON envelope, no base64 encoding. x-parser-schema-id: title: Binary Audio Frame description: Stream a raw binary audio frame to be transcribed. example: '"0000FF00000000FF0000000001010101010101010000"' bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeBinaryAudio bindings: [] extensions: *ref_0 - &ref_3 id: sttSpeechmaticsRealtimeV2ReceiveFinalize title: Stt speechmatics realtime v2 receive finalize description: Force end of utterance on Speechmatics Realtime v2 type: receive messages: - &ref_11 id: SpeechmaticsRealtimeFinalize contentType: application/json payload: - name: Finalize Message description: Force the current utterance to end without closing the stream. type: object properties: - name: type type: string description: finalize required: true headers: [] jsonPayloadSchema: type: object description: >- Force-finalize the current utterance and emit its final transcript. 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 the current utterance to end without closing the stream. example: |- { "type": "finalize" } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeFinalize bindings: [] extensions: *ref_0 - &ref_4 id: sttSpeechmaticsRealtimeV2ReceiveClose title: Stt speechmatics realtime v2 receive close description: Close audio stream on Speechmatics Realtime v2 type: receive messages: - &ref_12 id: SpeechmaticsRealtimeClose 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 finalizes 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: SpeechmaticsRealtimeClose bindings: [] extensions: *ref_0 - &ref_5 id: sttSpeechmaticsRealtimeV2SendPartialTranscript title: Stt speechmatics realtime v2 send partial transcript description: Receive partial transcript from Speechmatics Realtime v2 type: send messages: - &ref_13 id: SpeechmaticsRealtimePartialTranscript contentType: application/json payload: - name: Partial Transcript description: Interim transcription result (when partials are enabled). type: object properties: - name: type type: string description: partial_transcript required: true - name: transcript type: string description: Transcribed text so far. required: true - name: start_time type: number description: Start time of the segment in seconds. required: false - name: end_time type: number description: End time of the segment in seconds. required: false - name: confidence type: number description: Confidence score (0-1). required: false - name: language type: string description: Detected language of the segment. required: false - name: speaker type: string description: Speaker label, when diarization is enabled. required: false - name: channel type: string description: Channel label, when channel diarization is enabled. required: false headers: [] jsonPayloadSchema: type: object description: >- Interim transcription result. Emitted only when partials are enabled. required: - type - transcript properties: type: type: string const: partial_transcript x-parser-schema-id: transcript: type: string description: Transcribed text so far. x-parser-schema-id: start_time: type: number description: Start time of the segment in seconds. x-parser-schema-id: end_time: type: number description: End time of the segment in seconds. x-parser-schema-id: confidence: type: number description: Confidence score (0-1). x-parser-schema-id: language: type: string description: Detected language of the segment. x-parser-schema-id: speaker: type: string description: Speaker label, when diarization is enabled. x-parser-schema-id: channel: type: string description: Channel label, when channel diarization is enabled. x-parser-schema-id: x-parser-schema-id: title: Partial Transcript description: Interim transcription result (when partials are enabled). example: |- { "type": "partial_transcript", "transcript": "halo apa", "start_time": 0, "end_time": 0.8, "confidence": 0.82 } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimePartialTranscript bindings: [] extensions: *ref_0 - &ref_6 id: sttSpeechmaticsRealtimeV2SendFinalTranscript title: Stt speechmatics realtime v2 send final transcript description: Receive final transcript from Speechmatics Realtime v2 type: send messages: - &ref_14 id: SpeechmaticsRealtimeFinalTranscript contentType: application/json payload: - name: Final Transcript description: Finalized transcription segment. type: object properties: - name: type type: string description: final_transcript required: true - name: transcript type: string description: Finalized transcribed text. required: true - name: start_time type: number description: Start time of the segment in seconds. required: false - name: end_time type: number description: End time of the segment in seconds. required: false - name: confidence type: number description: Confidence score (0-1). required: false - name: language type: string description: Detected language of the segment. required: false - name: speaker type: string description: Speaker label, when diarization is enabled. required: false - name: channel type: string description: Channel label, when channel diarization is enabled. required: false headers: [] jsonPayloadSchema: type: object description: >- Finalized transcription segment with timing and optional diarization metadata. required: - type - transcript properties: type: type: string const: final_transcript x-parser-schema-id: transcript: type: string description: Finalized transcribed text. x-parser-schema-id: start_time: type: number description: Start time of the segment in seconds. x-parser-schema-id: end_time: type: number description: End time of the segment in seconds. x-parser-schema-id: confidence: type: number description: Confidence score (0-1). x-parser-schema-id: language: type: string description: Detected language of the segment. x-parser-schema-id: speaker: type: string description: Speaker label, when diarization is enabled. x-parser-schema-id: channel: type: string description: Channel label, when channel diarization is enabled. x-parser-schema-id: x-parser-schema-id: title: Final Transcript description: Finalized transcription segment. example: |- { "type": "final_transcript", "transcript": "Halo, apa kabar?", "start_time": 0, "end_time": 1.4, "confidence": 0.95 } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeFinalTranscript bindings: [] extensions: *ref_0 - &ref_7 id: sttSpeechmaticsRealtimeV2SendUtteranceEnd title: Stt speechmatics realtime v2 send utterance end description: Receive end-of-utterance from Speechmatics Realtime v2 type: send messages: - &ref_15 id: SpeechmaticsRealtimeUtteranceEnd contentType: application/json payload: - name: Utterance End description: End-of-utterance signal driven by the silence trigger. type: object properties: - name: type type: string description: utterance_end required: true - name: last_word_end type: number description: End time of the last word in the utterance, in seconds. required: false - name: channel type: string description: Channel label, when channel diarization is enabled. required: false headers: [] jsonPayloadSchema: type: object description: >- Signals the end of an utterance, emitted when the end-of-utterance silence trigger is configured. required: - type properties: type: type: string const: utterance_end x-parser-schema-id: last_word_end: type: number description: End time of the last word in the utterance, in seconds. x-parser-schema-id: channel: type: string description: Channel label, when channel diarization is enabled. x-parser-schema-id: x-parser-schema-id: title: Utterance End description: End-of-utterance signal driven by the silence trigger. example: |- { "type": "utterance_end", "last_word_end": 1.4 } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeUtteranceEnd bindings: [] extensions: *ref_0 - &ref_8 id: sttSpeechmaticsRealtimeV2SendError title: Stt speechmatics realtime v2 send error description: Receive error from Speechmatics Realtime v2 type: send messages: - &ref_16 id: SpeechmaticsRealtimeError 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: >- Provider error type (e.g., invalid_audio_type, not_authorised). required: false - name: message type: string description: Human-readable error description. required: true - name: status type: integer description: Provider status code, when available. required: false headers: [] jsonPayloadSchema: type: object description: Indicates an error occurred during recognition. required: - type - message properties: type: type: string const: error x-parser-schema-id: code: type: string description: Provider error type (e.g., invalid_audio_type, not_authorised). x-parser-schema-id: message: type: string description: Human-readable error description. x-parser-schema-id: status: type: integer description: Provider status code, when available. x-parser-schema-id: x-parser-schema-id: title: Error Response description: Indicates an error occurred during recognition. example: |- { "type": "error", "code": "invalid_audio_type", "message": "Unsupported audio encoding", "status": 400 } bindings: [] extensions: - id: x-parser-unique-object-id value: SpeechmaticsRealtimeError 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/speechmatics/realtime:v2 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: [] ````