zen-dub

Voice Synthesis

A voice synthesis model for text-to-speech, voice cloning, and multi-language dubbing. Produces natural-sounding speech with control over tone, pace, and emotion.

This model is coming soon. Join the waitlist at hanzo.chat.

Specifications

Capabilities

• Text-to-speech with natural prosody
• Multi-language voice synthesis (50+ languages)
• Voice cloning from reference audio
• Emotion and tone control
• Audio dubbing with lip-sync timing
• Batch audio generation

Usage

from hanzoai import Hanzo

client = Hanzo(api_key="hk-your-api-key")

# Coming soon
response = client.audio.speech.create(
    model="zen-dub",
    input="Welcome to the future of AI-powered voice synthesis.",
    voice="alloy",
    language="en",
)
response.stream_to_file("output.mp3")

See Also

• zen-dub-live -- Real-time voice synthesis
• zen-scribe -- Speech-to-text transcription
• zen-translator -- Multi-language translation