ReplicateText to speechComing soon

resemble-ai/chatterbox-turbo

Name: resemble-ai/chatterbox-turbo
Brand: Replicate

resemble-ai/chatterbox-turbo is a text to speech tool from Replicate that runs in the background and returns audio. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0325 per 1,000 characters of text.

Limits

Runs: In the background
Returns: audio
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`text` required	text	—	Text to synthesize into speech (maximum 500 characters). Supported paralinguistic tags you can include in your text: [clear throat], [sigh], [sush], [cough], [groan], [sniff], [gasp], [chuckle], [laugh] Example: "Oh, that's hilarious! [chuckle] Let me tell you more."
`seed`	number (whole)	—	Random seed for reproducible results. Leave blank for random generation.
`top_k`	number (whole) 1 to 2000	1000	Top-k sampling. Limits vocabulary to top k tokens at each step.
`top_p`	number 0.5 to 1	0.95	Nucleus sampling threshold. Lower values make output more focused.
`voice`	JSON	Andy	Pre-made voice to use for synthesis. Ignored if reference_audio is provided.
`temperature`	number 0.05 to 2	0.8	Controls randomness in generation. Higher values produce more varied speech.
`reference_audio`	text	—	Reference audio file for voice cloning (optional). Must be longer than 5 seconds. If provided, overrides the voice selection.
`repetition_penalty`	number 1 to 2	1.2	Penalizes token repetition. Higher values reduce repetition.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "resemble-ai/chatterbox-turbo",
    "input": {
      "text": "<text>"
    }
  }'