HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
resemble-ai
chatterbox
Python2025–2025
resemble-ai / chatterbox

chatterbox

SoTA open-source TTS

AI & Machine Learning
Explore on GitHubRead Hacker News discussions
15Distinct people
15Mentions
0Explicit recommenders
27.8KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

SoTA open-source TTS

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week15 dated mentions

Observed mentions: 2025-05-28 20:12:03 UTC to 2025-11-10 22:57:42 UTC. Weeks start Monday, UTC.

02462025-05-26 00:00:00 UTC to 2025-06-02 00:00:00 UTC (exclusive): 2 mentions; 2 submissions, 0 commentsMay 262025-06-02 00:00:00 UTC to 2025-06-09 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 comments2025-06-09 00:00:00 UTC to 2025-06-16 00:00:00 UTC (exclusive): 7 mentions; 2 submissions, 5 comments2025-06-16 00:00:00 UTC to 2025-06-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-06-23 00:00:00 UTC to 2025-06-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-06-30 00:00:00 UTC to 2025-07-07 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2025-07-07 00:00:00 UTC to 2025-07-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-07-14 00:00:00 UTC to 2025-07-21 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2025-07-21 00:00:00 UTC to 2025-07-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-07-28 00:00:00 UTC to 2025-08-04 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2025-08-04 00:00:00 UTC to 2025-08-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-08-11 00:00:00 UTC to 2025-08-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-08-18 00:00:00 UTC to 2025-08-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsAug 182025-08-25 00:00:00 UTC to 2025-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-01 00:00:00 UTC to 2025-09-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-08 00:00:00 UTC to 2025-09-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-15 00:00:00 UTC to 2025-09-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-22 00:00:00 UTC to 2025-09-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-09-29 00:00:00 UTC to 2025-10-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-10-06 00:00:00 UTC to 2025-10-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-10-13 00:00:00 UTC to 2025-10-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-10-20 00:00:00 UTC to 2025-10-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-10-27 00:00:00 UTC to 2025-11-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-11-03 00:00:00 UTC to 2025-11-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2025-11-10 00:00:00 UTC to 2025-11-17 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsNov 10

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
May 262025-05-26 00:00:00 UTC2025-06-02 00:00:00 UTC220
Jun 22025-06-02 00:00:00 UTC2025-06-09 00:00:00 UTC211
Jun 92025-06-09 00:00:00 UTC2025-06-16 00:00:00 UTC725
Jun 162025-06-16 00:00:00 UTC2025-06-23 00:00:00 UTC000
Jun 232025-06-23 00:00:00 UTC2025-06-30 00:00:00 UTC000
Jun 302025-06-30 00:00:00 UTC2025-07-07 00:00:00 UTC110
Jul 72025-07-07 00:00:00 UTC2025-07-14 00:00:00 UTC000
Jul 142025-07-14 00:00:00 UTC2025-07-21 00:00:00 UTC101
Jul 212025-07-21 00:00:00 UTC2025-07-28 00:00:00 UTC000
Jul 282025-07-28 00:00:00 UTC2025-08-04 00:00:00 UTC110
Aug 42025-08-04 00:00:00 UTC2025-08-11 00:00:00 UTC000
Aug 112025-08-11 00:00:00 UTC2025-08-18 00:00:00 UTC000
Aug 182025-08-18 00:00:00 UTC2025-08-25 00:00:00 UTC000
Aug 252025-08-25 00:00:00 UTC2025-09-01 00:00:00 UTC000
Sep 12025-09-01 00:00:00 UTC2025-09-08 00:00:00 UTC000
Sep 82025-09-08 00:00:00 UTC2025-09-15 00:00:00 UTC000
Sep 152025-09-15 00:00:00 UTC2025-09-22 00:00:00 UTC000
Sep 222025-09-22 00:00:00 UTC2025-09-29 00:00:00 UTC000
Sep 292025-09-29 00:00:00 UTC2025-10-06 00:00:00 UTC000
Oct 62025-10-06 00:00:00 UTC2025-10-13 00:00:00 UTC000
Oct 132025-10-13 00:00:00 UTC2025-10-20 00:00:00 UTC000
Oct 202025-10-20 00:00:00 UTC2025-10-27 00:00:00 UTC000
Oct 272025-10-27 00:00:00 UTC2025-11-03 00:00:00 UTC000
Nov 32025-11-03 00:00:00 UTC2025-11-10 00:00:00 UTC000
Nov 102025-11-10 00:00:00 UTC2025-11-17 00:00:00 UTC101

What Hacker News says

15 sources
RandomBK·Aug 3, 2025Submission

Show HN: Open-source Voice Cloning at 16x real-time: Porting Chatterbox to vLLM

Chatterbox TTS from ResembleAI (https://github.com/resemble-ai/chatterbox) is one of the most accessible and highest-quality Voice Cloning models available today. However, its implementation via HF Transformers left a lot of performance on the table. This is a pet project I've been building on-and-off. It ports the core of Chatterbox - a 0.5B Llama-architecture model - to vLLM. A lot of ugly hacks and workarounds were needed to make it work, but the end result works. Outputting at around the same quality level as the original implementation, this port is roughly 5-10x faster, generating a 40min benchmark output in around 2min30s wall time on a 3090 (or 4m30s on a 3060ti). That's almost 16x faster than real-time. High throughput like this can be itself transformative, enabling scale and efficiency that unblocks new use-cases. I look forwar
Read the rest
d to seeing what the community can do with this! Disclaimer: This is a personal community project not affiliated with ResembleAI, my employer, or any other entity. The project is based solely on publicly-available information. All opinions are my own and do not necessarily represent the views of my employer.
3 points · Open discussion
samagra14·Jun 30, 2025Submission

Ask HN: What Inference Server do you use to host TTS Models?

All the examples I have are highly unoptimized - For eg, Modal Labs uses FastAPI - https://modal.com/docs/examples/chatterbox_tts\ BentoML also uses FastAPI like service - https://www.bentoml.com/blog/deploying-a-text-to-speech-application-with-bentoml\ Even Chatterbox TTS has a very naive example - https://github.com/resemble-ai/chatterbox\ Tritonserver docs don’t have a TTS example. I am 100% certain that a highly optimized variant can be written with TritonServer, utilizing model concurrency and batching. If someone has implemented a TTS service with Tritonserver or has a better inference server alternative to deploy, please help me out here. I don’t want to reinvent the wheel.
1 points · Open discussion
andrewfromx·Jun 13, 2025Submission

Show HN: Automate final cut pro's XML language

Did you know the final cut pro xml import export is very powerful? Have you ever opened one of those xml files? https://github.com/andrewarrow/cutlass/blob/main/reference/p... That's a simple plus sign drawn with fcpxml shape language. But there's more! Way more: https://github.com/andrewarrow/cutlass/blob/main/FCPXMLv1_13... Almost 1000 line DTD file, you can do A LOT. And that's what "cutlass" aims to do. Open source golang project to let you slice, dice, and julienne fcpxml. Once you have code that can generate fcpxml you can do stuff like: https://www.youtube.com/watch?v=nGsnoAiVWvc This is all the top HN stories titles read by AI with screenshots and animations. (used https://github.com/resemble-ai/chatterbox and https://github.com/nari-labs/dia for voices) Do you have an idea for a video we could make using the power of cutlass? L
Read the rest
et me know!
3 points · Open discussion
echelon·Jun 12, 2025
Nevermind, this is just ~3/10 open, or not really open at all [1]: https://github.com/resemble-ai/chatterbox/issues/45#issuecom... > For now, that means we’re not releasing the training code, and fine-tuning will be something we support through our paid API (https://app.resemble.ai). This helps us pay the bills and keep pushing out models that (hopefully) benefit everyone. Big bummer here, Resemble. This is not at all open. For everyone stumbling upon this, there are better "open weights" models than Resemble's Chatterbox TTS: Zeroshot TTS: MaskGCT, MegaTTS3 Zeroshot VC: Seed-VC, MegaTTS3 These are really good robust models that score higher in openness. Unfortunately only Seed-VC is fully open. But all of the above still beat Resemble's Chatterbox in zero shot MOS (we tested a lot), especially the mega-OP Chinese models. (ByteDance slaps
Read the rest
with all things AI. Their new secretive video model is better than Veo 3, if you haven't already seen it [2]!) You can totally ignore this model masquerading as "open". Resemble isn't really being generous at all here, and this is some cheap wool over the eyes trickery. They know they retain all of the cards here, and really - if you're just going to use an API, why not just use ElevenLabs? Shame on y'all, Resemble. This isn't "open" AI. The Chinese are going to wipe the floor with TTS. ByteDance released their model in a more open manner than yours, and it sounds way better and generalizes to voices with higher speaker similarity. Playing with open source is a path forward, but it has to be in good faith. Please do better. [1] "10/10" open includes: 1. model code, 2. training code, 3. fine tuning code, 4. inference code, 5. raw training data, 6. processed training data, 7. weights, 8. license to outputs, 9. research paper, 10. patents. For something to be a good model, it should have 7/10 or above. [2] https://artificialanalysis.ai/text-to-video/arena?tab=leader...
In Chatterbox TTS
teraflop·Jun 11, 2025
> Every audio file generated by Chatterbox includes Resemble AI's Perth (Perceptual Threshold) Watermarker - imperceptible neural watermarks that survive MP3 compression, audio editing, and common manipulations while maintaining nearly 100% detection accuracy. Am I misunderstanding, or can you trivially disable the watermark by simply commenting out the call to the apply_watermark function in tts.py? https://github.com/resemble-ai/chatterbox/blob/master/src/ch... I thought the point of this sort of watermark was that it was embedded somehow in the model weights, so that it couldn't easily be separated out. If you're going to release an open-source model that adds a watermark as a separate post-processing step, then why bother with the watermark at all?
In Chatterbox TTS

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.