zen3-tts-hd

Broadcast-Quality Audio

Maximum fidelity text-to-speech for broadcast-quality audio production. Delivers studio-grade speech synthesis with exceptional naturalness, tonal accuracy, and audio clarity suited for professional media, podcasts, and commercial audio production.

Specifications

Capabilities

• Broadcast-quality audio output
• Studio-grade naturalness and tonal accuracy
• Extended voice range for diverse character voices
• Professional prosody control
• High-fidelity audio encoding
• Optimized for post-production workflows

API Usage

curl https://api.hanzo.ai/v1/audio/speech \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen3-tts-hd",
    "input": "In the beginning, there was silence. Then came the models.",
    "voice": "onyx",
    "response_format": "flac"
  }' \
  --output narration.flac

from hanzoai import Hanzo

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

response = client.audio.speech.create(
    model="zen3-tts-hd",
    input="In the beginning, there was silence. Then came the models.",
    voice="onyx",
    response_format="flac",
)

response.stream_to_file("narration.flac")

Try It

Open in Hanzo Chat

Resources

• Audio API -- Endpoint documentation
• Technical Report

See Also

• zen3-tts -- High-quality TTS with 40+ voices
• zen3-tts-fast -- Low-latency TTS for real-time agents
• Pricing -- Full pricing table