Chatterbox HD (Resemble AI) API

Chatterbox HD (Resemble AI) is a text-to-speech model by Resemble AI, available on the Venice API as tts-chatterbox-hd. It runs privately, with zero data retention.

Chatterbox HD (Resemble AI) API pricing

Model ID	Variant	Privacy	Price
`tts-chatterbox-hd`	Standard	Private	$50.00 per 1M characters

Chatterbox HD (Resemble AI) specifications

Spec	Value
Provider	Resemble AI
Released	Apr 17, 2026
Privacy	Private
Voices	9
Formats	wav

How to use the Chatterbox HD (Resemble AI) API

Send requests to POST https://api.venice.ai/api/v1/audio/speech with "model": "tts-chatterbox-hd" and your API key.

curl https://api.venice.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-chatterbox-hd",
    "input": "Private AI for everyone.",
    "voice": "Aurora",
    "response_format": "mp3"
  }' --output speech.mp3

Chatterbox HD (Resemble AI) API FAQ

How much does the Chatterbox HD (Resemble AI) API cost?

50.00 per 1M characters of input text, about

0.041 per minute of generated speech. Prices are in USD and can be paid in DIEM at parity.

What is the Chatterbox HD (Resemble AI) model ID?

Use tts-chatterbox-hd as the model parameter.

Is the Chatterbox HD (Resemble AI) API private?

Chatterbox HD (Resemble AI) is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

How many voices does Chatterbox HD (Resemble AI) have?

9 voices, for example Aurora, Blade, Britney. Output formats: wav.

Which endpoint does the Chatterbox HD (Resemble AI) API use?

Call POST /audio/speech.

Related models

Gradium TTS API: $47.50 per 1M characters
ElevenLabs Turbo v2.5 API: $62.50 per 1M characters
Orpheus TTS API: $62.50 per 1M characters
Qwen 3 TTS 0.6B API: $87.50 per 1M characters

Explore

By modality