You can run it for free here: https://huggingface.co/spaces/ResembleAI/Chatterbox
A bit on the nose that they used a sample from a professional voice actor (Jennifer English) as the default reference audio file in that huggingface tool.
Chatterbox TTS
191–197 of 197 posts
Re: Chatterbox TTS
#192Earlier quoted context omitted.
Hey — just pushed a big update that adds an (opt-in) frontend to test the API For now, there's just a textarea for input (so you'll have to copy the `.txt` contents) — but it's a lot easier than trying to finagle into a `curl` request Let me know if you have any issues!
(Didn't carefully read your reply. What follows are the results of cat-ing a text file in the CLI. Will give the new textbox a whirl in the morning PDT. A truly heartfelt thanks for helping me work with Chatterbox TTS!) Absolutely blown away. I fed it the first page of Gibson's "Neuromancer" and your incantation worked like a charm. Thanks for the shell script pipe mojo. Some other details: - 3:01 (3 mins, 1 sec) of…
An M4 Max with 128GB RAM? drools
What did your `it/s` end up looking like with that setup? MLX is fascinating to me. Apple made a really smart decision with the induction of its M-series.
With regard to the artifacts — this is definitely a known issue with Chatterbox. I'm unsure of where the current investigation on fixing it is at (or what the "tricks" are to avoid this), but it's definitely something that is eery among other things.
I appreciate your feedback through all of this!
Would love to have you on the Discord to keep in touch https://chatterboxtts.com/discord
Re: Chatterbox TTS
#193Earlier quoted context omitted.
(Didn't carefully read your reply. What follows are the results of cat-ing a text file in the CLI. Will give the new textbox a whirl in the morning PDT. A truly heartfelt thanks for helping me work with Chatterbox TTS!) Absolutely blown away. I fed it the first page of Gibson's "Neuromancer" and your incantation worked like a charm. Thanks for the shell script pipe mojo. Some other details: - 3:01 (3 mins, 1 sec) of…
An M4 Max with 128GB RAM? drools What did your `it/s` end up looking like with that setup? MLX is fascinating to me. Apple made a really smart decision with the induction of its M-series. With regard to the artifacts — this is definitely a known issue with Chatterbox. I'm unsure of where the current investigation on fixing it is at (or what the "tricks" are to avoid this), but it's definitely something that is eery a…
I'll follow up on Discord!
For those following along at home: frontend works (and is quite nice) after updating `vite.config.ts` with a proxy
server: {
proxy: {
// Proxy all API requests to the FastAPI backend
'/v1': 'http://localhost:4123',
},
},Re: Chatterbox TTS
#194Chatterbox is fantastic. I created an API wrapper that also makes installation easier (Dockerized as well) https://github.com/travisvn/chatterbox-tts-api/ Best voice cloning option available locally by far, in my experience.
Spent an hour trying to get it running with a RTX 50 series, no luck, tried with PyTorch 2.7.
Seems built for 2.6.
"chatterbox-tts 0.1.2 requires torch==2.6.0, but you have torch 2.7.0+cu128 which is incompatible. chatterbox-tts 0.1.2 requires torchaudio==2.6.0, but you have torchaudio 2.7.0+cu128 which is incompatible."
Re: Chatterbox TTS
#195Demos here: https://resemble-ai.github.io/chatterbox_demopage/ (not mine) This is a good release if they're not too cherry picked! I say this every time it comes up, and it's not as sexy to work on, but in my experiments voice AI is really held back by transcription, not TTS. Unless that's changed recently.
For English-only an non-commercial, Parakeet has been almost flawless for me.
https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2
I use it for real-time chat and generating subtitles. It can do a tv show in less than a minute on a 3090.
Whisper always hallucinated too much for me. It's more useful as a classifier.
Re: Chatterbox TTS
#196Demos here: https://resemble-ai.github.io/chatterbox_demopage/ (not mine) This is a good release if they're not too cherry picked! I say this every time it comes up, and it's not as sexy to work on, but in my experiments voice AI is really held back by transcription, not TTS. Unless that's changed recently.
It would be nice if there was some type of front-end integration that would present the user with a list of heteronyms found in the text and ask for clarification for each one. As well as having lists of common phrases to compare them against. There's really no excuse for an LLM to mispronounced "live feed" or "live here".
Re: Chatterbox TTS
#197Demos here: https://resemble-ai.github.io/chatterbox_demopage/ (not mine) This is a good release if they're not too cherry picked! I say this every time it comes up, and it's not as sexy to work on, but in my experiments voice AI is really held back by transcription, not TTS. Unless that's changed recently.
There seems to be a 40 second limit that nobody s talking about, once your audio crosses the 40 second length, it gets cut off