Model API

Chatterboxhd

Generate expressive, natural speech with Resemble AI's Chatterbox. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.

Model id

Use this in every request

resemble-ai/chatterboxhd/text-to-speech

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "resemble-ai/chatterboxhd/text-to-speech",
  "input": {
    "text": "example"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "resemble-ai/chatterboxhd/text-to-speech", "quote_id": "QUOTE_ID", "input": {"text":"example"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for resemble-ai/chatterboxhd/text-to-speech
Name	Type	Description
`text`required	string	Text to synthesize into speech.
`voice`	string (enum)	The voice to use for the TTS request. If neither voice nor audio are provided, a random voice will be used. One of: `Aurora`, `Blade`, `Britney`, `Carl`, `Cliff`, `Richard`, `Rico`, `Siobhan`, `Vicky`
`audio_url`	string (URL)	URL to the audio sample to use as a voice prompt for zero-shot TTS voice cloning. Providing a audio sample will override the voice setting. If neither voice nor audio_url are provided, a random voice will be used.
`exaggeration`	number	Controls emotion exaggeration. Range typically 0.25 to 2.0. Default: `0.5`
`cfg`	number	Classifier-free guidance scale (CFG) controls the conditioning factor. Range typically 0.2 to 1.0. For expressive or dramatic speech, try lower cfg values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher. If the reference speaker has a fast speaking style, lowering cfg to around 0.3 can improve pacing. Default: `0.5`
`high_quality_audio`	boolean	If True, the generated audio will be upscaled to 48kHz. The generation of the audio will take longer, but the quality will be higher. If False, the generated audio will be 24kHz. Default: `false`
`seed`	integer	Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed. Default: `0`
`temperature`	number	Controls the randomness of generation. Range typically 0.05 to 5. Default: `0.8`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "audio", "url": "https://…", "mime_type": "audio/mpeg", "thumbnail_url": null }
]

Pricing

up to · 1,000 ASCII characters$0.07/ run

The exact charge for your input comes from a quote. How charges settle