From cloning to creation, one platform does it all.
Voice Cloning
Clone Any Voice Instantly
Capture the essence of any voice from just 3 seconds of audio. Use 1 to 5 samples for higher fidelity. Choose Fast mode for instant results or Precise mode with transcription for studio-quality clones.
- From 3 seconds — up to 5 samples for best quality
- Automatic multilingual capability
- Preserves tone, accent & emotion
Voice Design
Create Voices from Text
Describe the voice you want and watch AI bring it to life. Perfect for creating unique characters, brand voices, or fictional personas that have never existed before.
- Natural language descriptions
- Fine-tune age, gender, accent
- Generate unlimited variations
Voice Library
Expressive Studio Voices
Access our curated library of high-fidelity voices with deep emotional control. From warm narrators to energetic presenters, find the perfect voice for any project.
- 9 premium studio voices included
- Emotional presets: happy, sad, angry...
- Professional quality output
Import Models
Bring Your Own Models
Already have voice models? Import them directly. ClonyVoice supports popular formats from XTTS, Coqui, and other frameworks. Your models, your control.
- XTTS & Coqui compatible
- Support for .pth, .onnx formats
- Easy drag & drop import
Multi-Voice Studio
Multi-Voice Dialogues & Video
Assign different voices to each sentence for realistic dialogues. Import scripts from .txt, .srt or .vtt files. Export as audio or video with synchronized avatars.
- Different voice per sentence
- Script import (.txt, .srt, .vtt)
- Video export with avatars (MP4)
Smart Editing
Real-Time Generation & Editing
Listen to each sentence as it generates in real time. Regenerate any single sentence without redoing the whole text. Built-in video editor with multi-track timeline.
- Listen as it generates, sentence by sentence
- Regenerate individual sentences
- Video editor with multi-track timeline
Audio Sources
Record, Upload, or Download
Record directly from your microphone with real-time VU meter. Upload audio files in any format. Or paste a YouTube URL and extract the voice automatically.
- Built-in mic recording with VU meter
- YouTube URL audio extraction
- Auto-denoising and Whisper transcription
Export & Share
Export Your Voice Models
Save your created voices in encrypted .clonyvoice packages. Import/export between machines securely. Manage projects with full take history.
- AES-encrypted voice packages
- Project management with take history
- Share voices with collaborators
Local API
Full REST API Built-in
Integrate ClonyVoice into your workflow with a comprehensive local API. Generate speech, manage voices, and control everything programmatically — no cloud dependency.
- RESTful API on localhost
- WebSocket real-time events
- Scoped API keys with rate limiting