Voice Cloning

​

Overview

• Personalize TTS — Generate speech in a specific voice
• Create characters — Unique voices for games or media
• Accessibility — Preserve a person’s voice
• Localization — Maintain voice consistency across languages

​

Getting Started

​

Download a Voice Cloning Model

izwi pull Qwen3-TTS-12Hz-0.6B-Base

​

Clone a Voice

1. Prepare a reference audio file (5-30 seconds of clear speech)
2. Use the voice for TTS generation

​

Using the Web UI

​

Step 1: Upload Reference Audio

1. Navigate to Voices in the sidebar and choose the clone flow
2. Upload a reference audio file
3. The audio should be:
   • 5-30 seconds long
   • Clear speech, minimal background noise
   • Single speaker

​

Step 2: Generate Speech

1. Enter the text you want to speak
2. Click Generate
3. Listen to the output in the cloned voice

​

Step 3: Save and Reuse

• Download generated audio
• Save the voice profile for future use

​

Using the CLI

izwi tts "This sentence will use the cloned voice." \
  --model Qwen3-TTS-12Hz-0.6B-Base \
  --reference-audio samples/reference.wav \
  --reference-text "This is the exact text spoken in the reference sample." \
  --output cloned.wav

izwi tts "This sentence uses a transcript file." \
  --model Qwen3-TTS-12Hz-1.7B-Base \
  --reference-audio samples/reference.wav \
  --reference-text-file samples/reference.txt \
  --output cloned-from-file.wav

izwi tts "This sentence uses my saved voice." \
  --model Qwen3-TTS-12Hz-0.6B-Base \
  --saved-voice-id voice_abc123 \
  --output saved-voice.wav

​

Using the API

​

Endpoint

POST /v1/audio/speech

​

Request (JSON)

​

Example (curl)

curl -X POST http://localhost:8080/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen3-TTS-12Hz-0.6B-Base",
    "input": "Hello, this is my cloned voice",
    "reference_audio": "<base64-audio>",
    "reference_text": "Hello, this is my cloned voice sample."
  }' \
  --output cloned.wav

​

Reference Audio Guidelines

​

Ideal Reference Audio

​

Good Examples

• Podcast clips
• Interview segments
• Voice memos
• Audiobook excerpts

​

Poor Examples

• Music with vocals
• Multiple speakers
• Heavy background noise
• Very short clips (under 3 seconds)
• Whispered or distorted speech

​

Tips for Best Results

1. Quality over quantity — A clear 10-second clip beats a noisy 30-second one
2. Natural speech — Avoid monotone or exaggerated delivery
3. Match content — Reference emotion should match desired output
4. Consistent volume — Avoid clips with volume changes
5. No music — Background music interferes with cloning

​

Available Models

​

Ethical Considerations

• Get consent — Only clone voices with permission
• Don’t impersonate — Never use cloned voices to deceive
• Respect privacy — Don’t clone voices without authorization
• Legal compliance — Follow applicable laws and regulations

​

Limitations

• Accent accuracy — May not perfectly capture all accents
• Emotional range — Cloned voices may have limited expressiveness
• Unique characteristics — Some voice qualities are hard to replicate
• Language — Best results in the model’s primary language

​

See Also

• Voices — Manage and reuse saved voices
• Voice Design — Create voices from descriptions
• Text-to-Speech — Standard TTS
• Models — Download models