Public API v1

Dub a Vietnamese audio file with a new voice

Transcribes the uploaded Vietnamese audio (Whisper STT), then re-synthesizes it with the chosen preset voice. Tokens are billed by the OUTPUT audio duration (same rate as the app, × the engine multiplier), charged only on success. Max file size: 10 MB.

post/api/v1/dub

Response

The re-voiced audio plus the transcript it was built from.

successboolean required

transcriptstring required

Vietnamese text transcribed from the uploaded audio.

voiceUsedstring required

Voice the audio was re-synthesized with.

audioUrlstring required

Presigned S3 download URL for the dubbed WAV.

audioUrlExpiresInnumber required

Seconds until audioUrl expires.

durationnumber required

Duration of the dubbed audio (seconds).

tokenCostnumber required

Tokens deducted (computed from the transcript).

Example response

{
  "success": true,
  "transcript": "Xin chào, đây là nội dung được phiên âm.",
  "voiceUsed": "Tuyen",
  "audioUrl": "https://s3.amazonaws.com/bucket/dub/job.wav?X-Amz-Expires=3600&...",
  "audioUrlExpiresIn": 3600,
  "duration": 5.2,
  "tokenCost": 80
}

Changes

No recorded changes to this endpoint across all 1 revision of this API.