보이스 체인저 검색
Poll a queued voice conversion. While the conversion is still running this returns status: "PROCESSING" as JSON; once it finishes it returns the converted audio bytes.
A completed response carries the audio alongside x-venice-audio-format, x-venice-audio-duration, x-venice-inference-time, x-venice-model-id and x-venice-model-name.
Only the account that queued a conversion can poll it. Any other queue_id — unknown, belonging to someone else, malformed, or older than the retrieve window — is reported the same way, as an invalid request id.
If the provider fails the conversion, the charge is refunded automatically and the response reports whether that refund succeeded in credits_refunded. The outcome is recorded, so polling again replays the same result rather than refunding twice.
When credits_refunded is false and the conversion was charged, the error message says what to do about it: a refund that was attempted and did not go through asks you to contact support and is retried by polling again, and a request id the provider no longer recognises is reported as too weak a verdict to reverse a charge on. A conversion that was never charged, or one already delivered, reports false with nothing further.
Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.
/audio/voice-changer/queue가 반환한 queue_id를 사용해 변환 상태를 확인하세요. 작업이 실행 중일 때는 status: "PROCESSING"이 포함된 JSON을 반환하며, 완료되면 audio/mpeg를 반환합니다. delete_media_on_completion을 true로 설정하면 동일 호출에서 저장 미디어를 정리하거나, 파일을 다운로드한 후 /audio/voice-changer/complete를 호출하세요.
보이스 체인저 모델은 /audio/retrieve에서 허용되지 않습니다.
Postman 컬렉션
추가 예제는 이 Postman 컬렉션을 참조하세요.인증
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
본문
The model that is running the conversion. Only voice-changer models are accepted on the /api/v1/audio/voice-changer endpoints.
"elevenlabs-voice-changer"
Pass this to /audio/voice-changer/retrieve to poll for the converted audio, and to /audio/voice-changer/complete when finished.
"0190f2c4-9c1e-7a3b-8f42-2c9d5e7a1b34"
Release the provider-held media as soon as this call returns the audio, so a separate /audio/voice-changer/complete call is unnecessary. The audio cannot be retrieved again afterwards.
false
응답
Conversion still processing, or the completed audio
The conversion is still running. Poll again.
PROCESSING "PROCESSING"
Recent average end-to-end time for this model in milliseconds. Use it to pace polling.
10000
Milliseconds elapsed since the conversion was queued.
4200