Audio
Chatterbox Voice Clone
Upload a short voice clip, type the words, and download a 24 kHz WAV in that voice.
Chatterbox by Resemble AI
Model licenses
Chatterbox-Turbo official fp32 ONNX and associated tokenizer/config assets · MIT
Retain the MIT copyright and permission notice. The original publisher model-card limitations and acknowledgements are preserved in the accompanying notice.
API reference
Submit via REST
Use your personal API key (msk_…) to create jobs for this workload from your own tools. Jobs started this way run on the same devices you connected on Your Devices — at least one has to be online.
https://cp.meshlabs.cloud/v1/organizations/jobsAuthenticate with X-Organization-Api-Key: msk_your_personal_api_key. The header name matches org keys; personal keys use the same endpoint.
POST https://cp.meshlabs.cloud/v1/organizations/job-inputs/presign with the same API key, upload your file to the returned upload_url, then pass download_url in job_spec (for example as input_image_url).Request body
{
"workload_type": "chatterbox-tts",
"job_spec": {
"prompt": "A photorealistic lighthouse at dusk",
"max_new_tokens": 256,
"repetition_penalty": 1.2
}
}job_spec fields
| Field | Required | Default | Description |
|---|---|---|---|
prompt | Yes | — | English text to speak. Paralinguistic tags such as [laugh] and [chuckle] are kept as tokens when they exist in the published tokenizer. |
input_audio_url | No | — | Reference clip to clone. Optional — catalog jobs without a clip use the bundled default_voice.wav fixture, not a user recording. Upload a file or record from this device; not both. |
max_new_tokens | No | 256 | Cap on sampled speech tokens after the start token. |
repetition_penalty | No | 1.2 | Official generation_config default is 1.2. |
cURL
curl -X POST https://cp.meshlabs.cloud/v1/organizations/jobs \
-H "X-Organization-Api-Key: msk_your_personal_api_key" \
-H "Content-Type: application/json" \
-d '{
"workload_type": "chatterbox-tts",
"job_spec": {
"prompt": "A photorealistic lighthouse at dusk",
"max_new_tokens": 256,
"repetition_penalty": 1.2
}
}'https://cp.meshlabs.cloud/v1/organizations/jobs/{job_id}Poll with the same API key until status is terminal (COMPLETED, FAILED, CANCELED, or MODERATION_BLOCKED). When content moderation is enabled, jobs may start in MODERATION_PENDING before entering the compute queue. Completed jobs include presigned download_url values on each output.
Create response
{
"id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"workload_type": "chatterbox-tts",
"status": "PENDING",
"job_spec_json": {
"prompt": "A photorealistic lighthouse at dusk",
"max_new_tokens": 256,
"repetition_penalty": 1.2
},
"work_units": [],
"outputs": [],
"created_at": "2026-06-08T12:00:00Z",
"updated_at": "2026-06-08T12:00:00Z"
}Completed response
{
"id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"workload_type": "chatterbox-tts",
"status": "COMPLETED",
"job_spec_json": {
"prompt": "A photorealistic lighthouse at dusk",
"max_new_tokens": 256,
"repetition_penalty": 1.2
},
"work_units": [
{
"id": "…",
"index": 0,
"status": "COMPLETED"
}
],
"outputs": [
{
"id": "…",
"output_type": "<output type>",
"filename": "<output filename>",
"size_bytes": 524288,
"download_url": "<presigned output download URL>"
}
],
"created_at": "2026-06-08T12:00:00Z",
"updated_at": "<completion timestamp>"
}Upload a reference clip and the words you want spoken. Chatterbox clones that voice and downloads a 24 kHz WAV — free voice cloning on devices you connect. It is English, and the model is MIT-licensed. It clones a clip you provide; it does not invent a celebrity voice, and it is not a seventy-language studio. The first run downloads the model onto your devices.