Table of Contents

Documentation

Learn how to use every feature of ClonyVoice.

Getting Started

Installation

After purchase, you receive an email with a download link (valid for 7 days). If the link has expired, log in to your account at clonyvoice.com to generate a new download link. The installer automatically sets up all required components including the AI models.

  1. Click the download link in your purchase confirmation email, or log in to your account at clonyvoice.com to download the installer
  2. Run the .exe installer and follow the setup wizard
  3. Wait for the installation to complete (this may take a few minutes as AI models are downloaded)
  4. Launch ClonyVoice from your desktop or Start menu
Screenshot coming soon

License Activation

Your license is activated automatically on first launch — the installer contains your personal activation token. No key or email entry is required. An internet connection is needed for this one-time activation. Each license covers one machine. If you have purchased multiple licenses, each installation automatically uses an available license from your account. To move a license to a different machine, deactivate it from your account at clonyvoice.com, then re-download and reinstall on the new machine.

Screenshot coming soon

Interface Overview

The interface features a top navigation bar with 6 tabs: Text to Audio (generate speech), Create a voice (clone or design voices), Transfer (VoiceStore), API (developer endpoints and keys), Projects (generation history and montages), and License (account and referral info). The header also includes a language selector, GPU/CPU mode toggle, and system stats in the bottom bar.

Video tutorial coming soon

Voice Cloning

How Voice Cloning Works

Voice cloning creates a digital model of a real voice from audio samples. Once cloned, this voice model can speak any text in any of the 10 supported languages.

Quick Mode

Quick mode creates an instant voice clone from your audio sample. Perfect for testing and previewing voices.

  1. Go to the "Create a voice" tab
  2. Select "Quick Mode" for clone mode
  3. Upload or record an audio sample (3-60 seconds)
  4. Give your voice a name and click "Clone"
  5. Your cloned voice appears in the voice selector, ready to use
Video tutorial coming soon

Precise Mode

Precise mode uses transcription to align the audio sample with its text content, producing a higher-quality voice clone. Recommended for production use.

  1. Go to the "Create a voice" tab and select "Precise Mode"
  2. Upload or record an audio sample (10-60 seconds recommended)
  3. The transcription is generated automatically — you can edit it for accuracy
  4. Click "Clone" and wait for processing (30-60 seconds)
  5. Your high-fidelity voice model is ready
Video tutorial coming soon

Multi-Sample Cloning

For the best voice fidelity, combine up to 5 different audio samples of the same voice. The AI will learn from all samples to create a more accurate voice model.

Screenshot coming soon

Tips for Best Results

docs_vc_tips_text

  • Use a quiet environment with minimal background noise
  • Record at a consistent volume and distance from the microphone
  • Include varied intonation — don't read in a monotone
  • Longer samples (10-30 seconds) give better results than very short ones
  • Avoid samples with music, other speakers, or sound effects

Voice Design

Creating Voices from Text

Voice Design lets you create entirely new voices by describing them in natural language. No audio sample is needed.

  1. Go to the "Create a voice" tab and select the "Design" mode
  2. Enter a description of the voice you want (e.g., "A warm, deep male voice with a calm tone")
  3. Click "Generate" to create the voice
  4. Preview the generated voice and regenerate if needed
  5. Save the voice to your library when satisfied
Video tutorial coming soon

Description Tips

docs_vd_tips_text

  • Describe age, gender, pitch, and tone
  • Mention accents or speaking styles if desired
  • Be specific: "energetic young woman" works better than "nice voice"
  • Generate multiple variations and pick your favorite

Text-to-Speech

Generating Speech

Once you have a voice (cloned, designed, or a built-in preset), you can generate speech from any text in the "Text to Audio" tab.

  1. Select a voice from the voice selector
  2. Type or paste your text in the input area
  3. Choose the output language
  4. Optionally select an emotion preset
  5. Click "Generate" and listen to the result
  6. The generated audio is saved automatically. You can export in WAV, MP3, or MP4 (video) format
Video tutorial coming soon

Emotion Presets

Apply emotional presets to make the generated speech more expressive. Six emotions are available: Neutral, Happy, Angry, Sad, Calm, and Confident. Each preset adjusts the intonation and expressiveness of the voice.

Screenshot coming soon

Multi-language Output

Any voice can speak in any of the 10 supported languages. Simply select the target language before generating. The voice characteristics are preserved while adapting pronunciation to the target language.

Import & Export

Exporting Voice Models

Export your voice models for backup or transfer to another machine using the Transfer tab.

  1. Go to the "Transfer" tab — your voices are listed on the left, grouped by category
  2. Select the voices you want to export using the checkboxes
  3. Click "Export" at the bottom, choose a save location, and save the .clonyvoice file
Screenshot coming soon

Importing Voice Models

Import voice models from .clonyvoice files or archives (.zip, .tar.gz, .7z) using the Transfer tab.

  1. Go to the "Transfer" tab — the import panel is on the right side
  2. Click "Choose a .clonyvoice file" and select your file
  3. Review the preview showing new and duplicate voices, then click Import
Screenshot coming soon

Troubleshooting

Slow generation

If generation is slow, make sure you're using GPU mode (requires NVIDIA GPU with CUDA). Close other GPU-intensive applications. On CPU-only mode, generation is naturally slower.

Poor voice quality

Use Precise mode with clean audio samples (10-30 seconds). Minimize background noise. Multiple samples improve fidelity. Avoid samples with music or multiple speakers.

Application crashes or won't start

Verify system requirements (Windows 11, 16 GB RAM). Ensure your antivirus isn't blocking the application. If the issue persists, re-download the installer from your account at clonyvoice.com and reinstall, or contact support.

License activation issues

License activation is automatic — it uses the token embedded in the installer filename. An internet connection is required for this one-time activation. If activation fails, re-download the installer from your account at clonyvoice.com and reinstall. To transfer your license to another machine, first deactivate the current one from your account dashboard.