Przejdź do nawigacji
ElevenAPIRealtime Translation

WebSocket

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

Uzgadnianie

WSS
/v1/translation/realtime

Nagłówki

xi-api-keystringOpcjonalny

Parametry zapytania

authorizationstringOpcjonalny
Your authorization bearer token.
target_languagestringWymagany

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

source_languagestringOpcjonalny

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

voice_idstringWymagany
Voice ID used for the translated speech output.
input_formatanyOpcjonalny
Audio encoding format for realtime translation input.
output_formatanyOpcjonalny
Audio encoding format for realtime translation output.
tts_model_idenumOpcjonalnyDomyślnie eleven_v4_turbo
TTS model used to synthesize the translated speech.
Dozwolone wartości:
apply_text_normalizationenumOpcjonalnyDomyślnie 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.

Dozwolone wartości:
eagernessenumOpcjonalnyDomyślnie 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.
Dozwolone wartości:
client_session_idstringOpcjonalny

Optional client-defined session identifier for tracking purposes.

enable_zrmbooleanOpcjonalnyDomyślnie 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.

Wyślij

inputAudioChunkobjectWymagany
Send a chunk of audio for translation.
OR
endOfStreamobjectWymagany
Signal that the audio stream has ended.

Odbierz

sessionStartedobjectWymagany
Sent by the server when the session is initialized.
OR
statusobjectWymagany
Session lifecycle update indicating the session has started or stopped.
OR
partialTranscriptobjectWymagany
Interim transcription of the source audio.
OR
finalTranscriptobjectWymagany
Final transcription of a segment of source audio.
OR
translationobjectWymagany
Translated text in the target language.
OR
audioobjectWymagany

Base64-encoded audio of the translated speech.

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

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

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

Translation failed for a segment; the session continues.

OR
Translate Audio Output ErrorobjectWymagany

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

OR
Translate Quota Exceeded ErrorobjectWymagany

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

OR
Translate Payment Issue ErrorobjectWymagany

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

OR
Translate Unaccepted Terms ErrorobjectWymagany

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