← All models
Dubs videos up to 10 minutes into 94 languages and 14 regional accents with cloned voices and lip-sync. Supports target accent and voice cloning strength controls, multiple speakers, and background audio preservation.
Example
Details
- Accepts
- text
Pricing
- Price
- 22.5 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| keyterms | array | Names and terms to get right in the dub, such as brand, product or people's names: they help the speech recognition catch these words and the translation keep them as written. Up to 1,000 terms, each at most 50 characters and 5 words, without the characters < > { } [ ] \. |
| video_urlrequired | string | Video to dub, up to 10 minutes long and with speech in its audio track. The speech is translated into the target language, and the speakers' lips are synced to the dubbed voices. |
| source_language | stringenum: auto, af, ak, am, ar, as… | Language spoken in the video. 'auto' (the default) detects it; set it explicitly if detection picks the wrong language. |
| target_languagerequired | stringenum: af, ak, am, ar, ar-EG, as… | Language to dub into, optionally with a regional dialect (e.g. 'es-MX', 'pt-BR'). Case-insensitive; for a language without dialects the region is ignored ('de-DE' = 'de'), and an unsupported dialect is rejected. |
| voice_cloning_strength | integer | How closely the dubbed voices match the original speakers, from 0 to 10. Higher keeps more of each speaker's voice and accent; lower sounds more natural in the target language. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The dubbed video, with the speakers' lips synced to the translated speech |