Skip to content

reference.mdx

Latest commit

 

History

History
74 lines (59 loc) · 3.99 KB

reference.mdx

File metadata and controls

74 lines (59 loc) · 3.99 KB
Raw
title Reference
sidebarTitle Reference
description Status lifecycle, limits, supported audio formats, languages, and output formats for the Voice Translate Job API.
public true

Result Status Lifecycle

Each target result progresses through these statuses independently:

Job created; source file not yet uploaded. Source file received; processing has not started. Translation in progress. Result is ready to download. Result has been downloaded; assets marked for deletion.

A target can transition to failed from any non-terminal state. When a target fails, the error field contains a description of the failure.

Limits

Limit Value
Maximum file size 1 GB (1,073,741,824 bytes)
Maximum source duration 3 hours
Time to upload after job creation 5 minutes
Time to download results after upload 1 hour
Maximum concurrent jobs per customer 10
Maximum concurrent jobs per customer (files > 100 MB) 2
Maximum targets per job No limit (constrained by storage quota)

After all results are downloaded or the job expires, the job is deleted and returns 404. Usage is billed based on the duration of the source audio.

Source audio over 3 hours is rejected, even if the file is under 1 GB. For longer recordings, split the source into chunks and submit each as its own job.

Supported Source Audio Formats

  • audio/mpeg
  • audio/wav
  • audio/ogg
  • audio/flac
  • audio/mp4
  • audio/webm

Supported Languages

Source and target languages match the real-time Voice API. source_language is optional; if omitted, the language is detected automatically.

Supported Output Formats

Each target specifies a type for the desired output format.

Type Description
text/plain Plain text transcript
application/x-subrip SRT subtitle file with original timecodes
audio/opus Opus audio
audio/flac FLAC audio
audio/pcm;encoding=s16le;rate=16000 PCM 16-bit signed LE, 16 kHz
audio/pcm;encoding=s16le;rate=24000 PCM 16-bit signed LE, 24 kHz
audio/pcm;encoding=ulaw;rate=8000 PCM u-law, 8 kHz
audio/pcm;encoding=alaw;rate=8000 PCM A-law, 8 kHz
audio/x-matroska;codecs=aac Matroska with AAC
audio/x-matroska;codecs=flac Matroska with FLAC
audio/x-matroska;codecs=opus Matroska with Opus
audio/x-matroska;codecs=pcm_s16le;rate=16000 Matroska with PCM 16 kHz
audio/x-matroska;codecs=pcm_s16le;rate=24000 Matroska with PCM 24 kHz
video/mp2t;codecs=aac MPEG-TS with AAC
video/mp2t;codecs=opus MPEG-TS with Opus
audio/ogg;codecs=flac Ogg with FLAC
audio/ogg;codecs=opus Ogg with Opus
audio/webm;codecs=opus WebM with Opus