Skip to main content
POST
Re-voice a recording with a cloned voice
Speech-to-speech: keeps the words and timing of a recording and replaces the voice with one of your cloned voices. Audio can be up to 5 minutes. Costs 10 credits per minute, rounded up (minimum 1). Poll Poll voiceover status with conversion.id.

Authorizations

Authorization
string
header
required

An Unsora API key (uns_…). A Clerk session token also works.

Body

application/json
voice_id
string
required

Id of one of your cloned voices (GET /voice-clones). Preset voices are rejected.

source_url
string<uri>

Recording to re-voice. Send this or source_asset_id.

source_asset_id
string

One of your AUDIO or VIDEO assets instead of source_url.

output_format
enum<string>
default:mp3
Available options:
mp3,
wav

Response

Job queued

success
boolean
required
conversion
object
required
creditsDeducted
integer
creditsRemaining
integer