Voice Fix

POST/api/v2/voice-fix
25 credits per video

Replace the spoken voice in a talking video with a cloned voice — an influencer's voice (influencer_id) or any voice the team owns (voice_id, e.g. created via /api/v2/voice-clone) — while preserving the original lip-sync, timing, and background audio. Ideal for unifying narration across clips without re-shooting or re-rendering.

Request body

video_url

Sign in to upload or import from your library.

Public URL of the talking video whose voice should be replaced.

influencer_id

Sign in to pick from your trained influencers.

ID of the influencer whose cloned voice the video should be re-spoken in. The video keeps its original lip-sync and timing. Optional when voice_id is provided; at least one of influencer_id / voice_id is required.

voice_id

Generate an API key to pick from your voices.

A specific voice ID. With influencer_id it must belong to that influencer (defaults to the influencer's most recent voice when omitted). Without influencer_id it can be any voice the team owns — e.g. a standalone voice created via /api/v2/voice-clone or /api/v2/voice-design.

realism_preset

Microphone realism applied to the converted voice track. 'ugc-phone' (default) emulates a phone mic, 'pro-mic' a studio mic, 'off' keeps it clean.

workspace_id
Sign in to run the playground
Sign in

Request example 

curl -X POST "https://influencerstudio.com/api/v2/voice-fix" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Output

Run the model to see results

Real outputs will stream into this panel as the request completes.