Chatterbox TTS
Source: https://github.com/resemble-ai/chatterbox
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Open TTS family from Resemble AI (including a 350M Chatterbox-Turbo for low-latency English voice agents) with every generated file carrying an imperceptible PerTh neural watermark and published extraction code.",
"source_type": "repository",
"availability": "available",
"dependencies": [
"perth watermarker"
],
"source_owner": "Resemble AI",
"next_check_at": "2026-10-24T00:00:00.000Z",
"upstream_updated_at": "2026-07-21T12:27:05.000Z"
}Evidence claims
- [upstream_claim] README: Chatterbox is a family of state-of-the-art open-source TTS models by Resemble AI; Chatterbox-Turbo is a 350M parameter model for low-latency English voice agents. · locator: README, intro source
- [upstream_claim] README 'Built-in PerTh Watermarking for Responsible AI': every generated audio file includes Resemble AI's Perth neural watermark, said to survive MP3 compression and common edits; watermark extraction script provided. · locator: README, PerTh Watermarking and extraction sections source
- [sourced_fact] GitHub metadata: MIT, not archived, last push 2026-07-21. · locator: repository metadata source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | MIT | permitted | permitted | permitted | unknown | MIT per GitHub. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Weights license and hosting terms were not inspected. |