SLNG · AsyncAPI Specification
SLNG Gateway API - SLNG STT
Version 0.1.0
SLNG Gateway API
View Spec
View on GitHub
CompanySpeechVoiceSpeech to TextText to SpeechVoice AIVoice AgentsTranscriptionSpeech RecognitionArtificial IntelligenceAPI GatewayAsyncAPIWebhooksEvents
Channels
/v1/stt/slng/openai/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.
/v1/stt/slng/deepgram/nova:3-en
Stream real-time English transcripts from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partials, finals, and speaker diarization.
/v1/stt/slng/deepgram/nova:3-te
Stream real-time Telugu speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-mr
Stream real-time Marathi speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-kn
Stream real-time Kannada speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-es
Stream real-time Spanish speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-in
Stream real-time Indonesian speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-hi
Stream real-time Hindi speech-to-text from SLNG-hosted Deepgram Nova 3 over WebSocket with low-latency partial and final transcripts and VAD.
/v1/stt/slng/deepgram/nova:3-multi
Stream real-time multilingual transcripts from SLNG-hosted Deepgram Nova 3 over WebSocket with automatic language detection across supported languages.
Messages
DeepgramSttResultsMulti
Results
Deepgram transcription result — partial or final, determined by is_final.
SlngDeepgramNova3MultiSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 multi-language STT session.
DeepgramSttResultsIn
Results
Deepgram transcription result — partial or final, determined by is_final.
SlngDeepgramNova3InSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Indonesian STT session.
DeepgramSttResultsHi
Results
Deepgram transcription result — partial or final, determined by is_final.
SlngDeepgramNova3HiSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Hindi STT session.
DeepgramSttResultsEs
Results
Deepgram transcription result — partial or final, determined by is_final.
SlngDeepgramNova3EsSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Spanish STT session.
DeepgramSttError
Error
Error from the Deepgram backend or gateway.
DeepgramSttResultsEn
Results
Deepgram transcription result — partial or final, determined by is_final.
DeepgramSttResultsTe
Results
Deepgram transcription result — partial or final, determined by is_final.
DeepgramSttResultsTa
Results
Deepgram transcription result — partial or final, determined by is_final.
DeepgramSttResultsMr
Results
Deepgram transcription result — partial or final, determined by is_final.
DeepgramSttResultsKn
Results
Deepgram transcription result — partial or final, determined by is_final.
DeepgramSttMetadata
Metadata
Deepgram session metadata. Sent when the backend connects and again after the session ends with final statistics. This is informational — do not wait for it before streaming audio.
KeepaliveMessage
Keepalive Message
Keep the WebSocket connection alive during silence.
DeepgramSttBinaryAudio
Binary Audio Frame
Stream raw binary PCM audio frames to be transcribed. Sent as binary WebSocket frames (NOT JSON). Recommended chunk size is 8192 bytes (~256ms at 16kHz linear16). Start streaming immediately after the init message — do not wait for the Metadata response.
SlngDeepgramNova3EnSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 English STT session.
SlngDeepgramNova3TeSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Telugu STT session.
SlngDeepgramNova3TaSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Tamil STT session.
SlngDeepgramNova3MrSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Marathi STT session.
SlngDeepgramNova3KnSttInitRequest
Init Request
Initialize an SLNG-hosted Deepgram Nova 3 Kannada STT session.
SttErrorResponse
Error Response
Indicates an error occurred during recognition.
SlngWhisperSttFinalTranscript
Final Transcript
Final Whisper transcription result with segment-level detail.
SlngWhisperSttPartialTranscript
Partial Transcript
Interim Whisper transcription result, updated as more audio is processed.
SlngWhisperSttReadyResponse
Ready Response
Indicates the Whisper session is ready to receive audio.
SttCloseMessage
Close Message
Signal end of audio stream and close the connection.
SttFinalizeMessage
Finalize Message
Force-finalize buffered audio tokens without closing the connection.
SttAudioMessage
Audio Message
Stream an audio frame to be transcribed.
SlngWhisperLargeV3SttInitRequest
Init Request
Initialize an SLNG-hosted Whisper Large v3 STT session.
Servers
wss
production
Production
wss
staging
Staging