Hoppa till navigering
ElevenAPIRealtime Translation

WebSocket

The Realtime Translation WebSocket API streams translation audio continuously to a target language given source audio. Currently for enterprise workspaces only.

Handskakining

WSS
/v1/translation/realtime

Headers

xi-api-keystringValfri

Frågeparametrar

authorizationstringValfri
Your authorization bearer token.
target_languagestringObligatorisk

Target language as an ISO 639 code (e.g. de, es, fr, zh).

source_languagestringValfri

Source language as an ISO 639 code. When omitted the server auto-detects the spoken language.

voice_idstringObligatorisk
Voice ID used for the translated speech output.
input_formatanyValfri
Audio encoding format for realtime translation input.
output_formatanyValfri
Audio encoding format for realtime translation output.
tts_model_idenumValfriStandard är eleven_v4_turbo
TTS model used to synthesize the translated speech.
Tillåtna värden:
apply_text_normalizationenumValfriStandard är off

This parameter controls text normalization with three modes: ‘auto’, ‘on’, and ‘off’. When set to ‘auto’, the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With ‘on’, text normalization will always be applied, while with ‘off’, it will be skipped.

Tillåtna värden:
eagernessenumValfriStandard är medium
How eagerly translation starts while the speaker is still talking. 'high' starts translating soonest for the lowest latency. 'low' waits for more of the sentence, giving higher quality translations with more delay.
Tillåtna värden:
client_session_idstringValfri

Optional client-defined session identifier for tracking purposes.

enable_zrmbooleanValfriStandard är false

When enable_zrm is set to true, zero retention mode will be used for the request. Sensitive content (transcripts, translations, and TTS text) is not written to application logs or session history. Zero retention mode may only be used by enterprise customers.

Skicka

inputAudioChunkobjectObligatorisk
Send a chunk of audio for translation.
OR
endOfStreamobjectObligatorisk
Signal that the audio stream has ended.

Ta emot

sessionStartedobjectObligatorisk
Sent by the server when the session is initialized.
OR
statusobjectObligatorisk
Session lifecycle update indicating the session has started or stopped.
OR
partialTranscriptobjectObligatorisk
Interim transcription of the source audio.
OR
finalTranscriptobjectObligatorisk
Final transcription of a segment of source audio.
OR
translationobjectObligatorisk
Translated text in the target language.
OR
audioobjectObligatorisk

Base64-encoded audio of the translated speech.

OR
errorobjectObligatorisk
Error encountered during translation.
OR
Translate Auth ErrorobjectObligatorisk
Authentication failed for the session.
OR
Translate Rate Limited ErrorobjectObligatorisk
The request rate limit was reached.
OR
Translate Queue Overflow ErrorobjectObligatorisk
Audio was sent too frequently and the session was terminated.
OR
Translate Input ErrorobjectObligatorisk

An input message could not be handled; check the message format.

OR
Translate Transcriber ErrorobjectObligatorisk
The transcriber failed to process the audio.
OR
Translate Translation ErrorobjectObligatorisk

Translation failed for a segment; the session continues.

OR
Translate Audio Output ErrorobjectObligatorisk

Audio output for a segment failed or was dropped; the session continues.

OR
Translate Quota Exceeded ErrorobjectObligatorisk

The workspace is out of credits; the session is closed.

OR
Translate Payment Issue ErrorobjectObligatorisk

The workspace has a payment issue or is suspended; the session is closed.

OR
Translate Unaccepted Terms ErrorobjectObligatorisk

The workspace has not accepted terms required for this feature; the session is closed.