Voice Cloning API
Voice cloning API: clone a voice from a few seconds of audio
Save a voice once from a short clip, then send its name or ID with any text to hear it speak.
Cloud API on the Starter and Premium plans, or the Desktop API on your own computer.
# 1. Clone a voice from a 5 to 30 second WAV clipcurl -X POST https://api.vcp.name/v1/voices \ -H "Authorization: Bearer $VCP_API_KEY" \ -H "Content-Type: application/json" \ -d '{"name": "Narrator", "audio_url": "https://example.com/narrator.wav"}' # 2. Speak any text in itcurl -X POST https://api.vcp.name/v1/speech \ -H "Authorization: Bearer $VCP_API_KEY" \ -H "Content-Type: application/json" \ -d '{"text": "Thanks for watching. See you next week.", "voice": "Narrator"}'What developers build with it
Cloning is zero-shot: no training step, no waiting. The Cloud API takes a WAV clip of 5 to 30 seconds.
- A creator's own voice reading new scripts, without recording each one
- Consistent character voices across every episode of a series
- Localized lines in the original speaker's voice
{ "id": "04bd0571-e2c8-4d5b-a3cc-e56f85773abf", "type": "voice_clone", "status": "succeeded", "result": { "voice": { "id": "7c9e6679-7425-40de-944b-e07fc1f90ae7", "name": "Narrator", "type": "clone" }, "transcript": "Hi, this is my normal speaking voice." }, "tokens_charged": 42, "finished_at": "2026-10-30T00:18:01Z"}Let your users clone their own voice inside your app.
Endpoints
Voice cloning endpoints
| Method | Path | What it does |
|---|---|---|
| POST | /v1/voices | Clone a voice from a WAV clip |
| GET | /v1/voices | List your voices |
| PATCH | /v1/voices/{id} | Rename a voice |
| DELETE | /v1/voices/{id} | Delete a voice |
| POST | /v1/speech | Speak text in a cloned voice |
Desktop API
Run the API on your own computer
Every desktop plan includes a local API on Windows and Mac. It needs no key and answers requests from your computer while the app is open.
curl -X POST "http://127.0.0.1:8100/api/v1/generation/clone?sync=true" \ -H "Content-Type: application/json" \ -d '{ "voice_id": "VOICE_ID", "target_text": "Thanks for watching. See you next week.", "language": "English" }'Desktop API endpoints
| Method | Path | What it does |
|---|---|---|
| POST | /api/v1/voices | Save a reference clip and transcript as a voice |
| POST | /api/v1/generation/clone | Generate speech in a cloned voice |
| POST | /api/v1/generation/clone/stream | Stream cloned speech as it generates |
| GET | /api/v1/voices | List saved voices |
Create a key and send your first request in a few minutes.
FAQ
Common Questions
The Cloud API takes a WAV clip of 5 to 30 seconds and transcribes it for you unless you send the transcript. In the Desktop API, 3 to 10 seconds of clear speech gives the best clone, with the transcript as ref_text.
Yes. In the Cloud API, POST /v1/voices saves the voice and you pass its name or ID as voice on POST /v1/speech. In the Desktop API, save the clip with POST /api/v1/voices and pass the voice_id to /api/v1/generation/clone.
In the Desktop API, yes, with the Qwen3-TTS model: set emotion and intensity to choose from 13 emotions at 5 intensities. With OmniVoice, and in the Cloud API, emotion comes from the reference clip.
In the Desktop API, yes. POST /api/v1/generation/clone/stream returns audio as it is generated, so playback starts before the line is finished. The Cloud API returns the finished clip as a job.
Explore
Related APIs
Text to speech
Turn text into speech with preset or cloned voices.
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.
Voice changer
Re-voice a recording while keeping its timing and emotion.
Audiobooks
Narrate a manuscript with a voice for every character.