Voice Creator Pro API

AI voice and video API for speech, dubbing, video generation and editing

Build with AI voice and video at scale. Generate speech, clone and design voices, transcribe audio, and dub, caption or clip videos through one API.

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

Join the cloud API waitlist Get the desktop app

POST/api/v1/tts/generate

curl -X POST "http://127.0.0.1:8100/api/v1/tts/generate?sync=true" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to the product tour.",
    "speaker": "Vivian",
    "language": "English"
  }'

Quickstart

Make your first request in three steps

The desktop app runs the API on your computer. Call it from any language that can send HTTP requests.

1
Install the desktop app
Every desktop plan includes the API, on Windows and Mac.
2
Turn on the API
Open Settings > API & MCP and enable it.
3
Send a request
With the app open, send a request from your code. No API key needed.

GET/api/v1/health

# Confirm the API is on before your first request
curl http://127.0.0.1:8100/api/v1/health

Full API reference

Capabilities

Explore the API by feature

Text to speech

Turn text into speech with preset speakers in 10 languages.

/api/v1/tts/generate

Voice cloning

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

/api/v1/generation/clone

Voice design

Describe a voice in words and generate speech in it.

/api/v1/generation/design

Speech to text

Transcribe audio with word timestamps and speaker labels.

/api/v1/transcription/start

Dubbing

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

/api/v1/dubbing/projects

Subtitles

Generate SRT caption files with word-level timing.

/api/v1/transcription/start

Clips

Cut long videos into short, captioned clips.

/api/v1/clips/projects

AI Cut

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

/api/v1/aicut/projects

Avatars

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

/api/v1/talking-head/videos

Voice changer

Re-voice a recording while keeping its timing and emotion.

/api/v1/conversion/convert

Audiobooks

Narrate a manuscript with a voice for every character.

/api/v1/audiobook/projects

Need any of these in the cloud instead of running locally?

Join the cloud API waitlist

FAQ

Common Questions

Not yet. Today the API runs locally with the desktop app. A cloud API is in the works: join the waitlist on this page to hear when early access opens.

Every desktop plan, on Windows and Mac. Turn it on in the app under Settings > API & MCP. VCP Cloud doesn't include API access.

Nothing extra. The API comes with the desktop app, a one-time purchase starting at $54.99, and there are no per-request fees.

Yes. The API server runs inside the desktop app, so requests only work while the app is open on that computer.

No. The local API has no authentication: it only accepts requests on your own computer.

Speech features do: text to speech, cloning, voice design, transcription and the voice changer run on your computer. Clips, AI Cut and audiobook speaker detection use the LLM you set in the app, so they need a connection unless that LLM runs locally too.

Not today. The local API is built for producing finished audio and video, such as narration, dubbing and clips, rather than low-latency conversation with callers.