Introducing Song Creator Pro — create music with AI, locally on your device. Try it now →
Voice Creator Pro logoVoice Creator Pro
Try For Free

Voice Changer API

Voice changer API: change the voice, keep the performance

Send a recording and a target voice, and get the same performance back in that voice.

Available now as a local API in the desktop app. Cloud API coming soon.

Join the cloud API waitlistGet the desktop app
POST/api/v1/conversion/convert
printf '{"source_audio_base64": "%s", "target_voice_id": "VOICE_ID"}' \
  "$(base64 < my-take.wav | tr -d '\n')" > body.json
 
curl -X POST "http://127.0.0.1:8100/api/v1/conversion/convert?sync=true" \
  -H "Content-Type: application/json" \
  -d @body.json

What developers build with it

The conversion keeps the words, pacing, inflection and emotion of the source. Only the voice changes.

  • Acted performances re-voiced into a character's voice
  • Scratch recordings turned into the final voice without re-recording
  • One voice actor covering several characters in a game
See the product page
Response
{
  "success": true,
  "status": "Generated successfully",
  "audio_base64": "UklGRiQAAABXQVZFZm10..."
}

Need voice conversion as a cloud endpoint?

Join the cloud API waitlist

Endpoints

Voice changer endpoints

MethodPathWhat it does
POST/api/v1/conversion/convertConvert a recording to a target voice
GET/api/v1/conversion/modelsList voice conversion models
GET/api/v1/conversion/progressPoll a conversion started without sync
POST/api/v1/conversion/stopCancel a conversion

Quickstart

Make your first request in three steps

Install the app, turn on the API and send your first request.

API reference

Full API reference

Every endpoint, with its parameters and responses.

Cloud API

Join the cloud API waitlist

We're building a cloud API. Pick the features you need and roughly how much you'd use, and your answers decide which ones come first.

Which features do you need?

We'll only email you about the API. Unsubscribe anytime.

FAQ

Common Questions

The voice changer starts from a recording and keeps its delivery: timing, inflection, emotion and accent. Text to speech starts from text and the model decides the delivery.

Any saved voice in your library, passed as target_voice_id, or a short reference clip sent as target_audio_base64.

No. Through the desktop app's local API, conversion runs on your own computer and the audio never leaves it.

Yes. GET /api/v1/conversion/models lists the available models. Pass model_family on the convert request to pick one.

Explore

Related APIs

Text to speech

Turn text into speech with preset speakers in 10 languages.

Voice cloning

Clone a voice from a short clip and speak new text with it.

Voice design

Describe a voice in words and generate speech in it.

Speech to text

Transcribe audio with word timestamps and speaker labels.

Dubbing

Dub videos into 21 languages, keeping each speaker's voice.

Subtitles

Generate SRT caption files with word-level timing.

Clips

Cut long videos into short, captioned clips.

AI Cut

Remove silences, filler words and bad takes, then render.

Avatars

Make a lip-synced talking-head video from one photo.

Audiobooks

Narrate a manuscript with a voice for every character.