GEgenaipro
Voice AI Beta — Max

Create Task from SRT

Changed on

Dub an SRT subtitle file: every cue is spoken and placed at its timestamp, producing one audio file. Same voice and control fields as POST /v1/tts/max, with srt_content instead of content. Cost: ⌈characters × 0.7⌉ credits over all cues.

Limits: at most 1000 cues and 3 hours; each cue must contain speakable text, at most 4500 billable characters and at most 15 emotion tags. Errors name the offending cue (e.g. "Cue 12 exceeds 4500 characters for this voice").

Rate limit: 10 requests/minute

post/v1/tts/max/srt

Request

Request body

titlestring
srt_contentstring required

Full SRT file content

voice_idstring
voice_asset_idstring
tts_model'max-hd' | 'max-turbo'
languagestring
speednumber
volumenumber
pitchinteger
callback_urlstring

Example request

{
  "srt_content": "1\n00:00:00,000 --> 00:00:02,500\nHello there.\n\n2\n00:00:03,000 --> 00:00:05,000\n{happy}Welcome back!{/happy}\n"
}

Response

Task created

idstring

Task ID (poll via the provider's GET /{id})

status'pending' | 'cloning' | 'queued' | 'processing' | 'merging' | 'process_merging' | 'completed' | 'failed'

Voice AI Beta task lifecycle: pending → cloning (clone flow only) → queued → processing → merging → process_merging → completed | failed.

providerstring
total_lengthinteger

Billable characters (encoder units ≈ UTF-8 bytes)

costinteger

Credits deducted for this task

Example response

{
  "status": "completed",
  "provider": "lyra"
}

Changes