alt.freeweights.speech / chatterbox-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.speechSubject:

chatterbox-4bit

Date: 2026-11-15Commit: f1d7b96Signed: 2DC28CC7B26A283B ✓

Text to speech model with 693M parameters. Safetensors weights, 612 MB in all. Published by mlx-community under Apache-2.0.

693M params612MBchatterbox-4bitsafetensorspermissive
FactsParams693MSize612 MBFormatssafetensorsTasktext to speechLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/chatterbox-4bit
# manifest sha256 f2040f36128d… · 612 MB · 10 files
$ fw verify ./chatterbox-4bit mlx-community/chatterbox-4bit
From sourceHosted (signed)mlx-community/chatterbox-4bitLast check: 2026-11-15 05:09 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of chatterbox.

Works with

Overview

Size
612 MB
Weights
607 MB (safetensors)
Parameters
693M
Formats
safetensors
Task
text to speech
License
Apache-2.0 (permissive)
Files
10, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.speech
Lineage

Original release from the publisher.

Base model: ResembleAI/chatterbox

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:09 UTCpassed

Model card

From the publisher at commit f1d7b96. Shown as plain text with links; images open at the publisher.

mlx-community/chatterbox-4bit#

This model was converted to MLX format from ResembleAI/chatterbox using mlx-audio version 0.2.7. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-audio
CLI Example:#
python -m mlx_audio.tts.generate --model mlx-community/chatterbox-4bit --text "Hello, this is a test."
Python Example:#
from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio
model = load_model("mlx-community/chatterbox-4bit")
generate_audio(
    model=model, text="Hello, this is a test.",
    file_prefix="test_audio",
)
Voice Cloning:#
from mlx_audio.tts.generate import generate_audio

generate_audio(
    text="Hello, this is a test of Chatterbox TTS.",
    model="mlx-community/chatterbox-4bit",
    ref_audio="path_to_file.wav",
    ref_text="Text transcript", # Optional
    file_prefix="vc_output",
)

Multilingual Quickstart#

Generate speech in 23 languages by specifying the lang_code parameter. The model automatically handles pronunciation, intonation, and language-specific phonemes.

from mlx_audio.tts.generate import generate_audio

generate_audio(
    text="Olá, tudo bem?",
    model="mlx-community/chatterbox-4bit",
    lang_code="pt",
    file_prefix="multilingual_output",
)
Supported Languages#
CodeLanguageCodeLanguageCodeLanguage
arArabicheHebrewnoNorwegian
daDanishhiHindiplPolish
deGermanitItalianptPortuguese
elGreekjaJapaneseruRussian
enEnglishkoKoreansvSwedish
esSpanishmsMalayswSwahili
fiFinnishnlDutchtrTurkish
frFrenchzhChinese

Files

10 files · 612 MBWeights 607 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256
FileSizesha256
.gitattributes1.56 KB73b4221dd26d36797b93ed5bc49bb5435507ac340e39d4ad6325976d187fb73f
Cangjie5_TC.json1.92 MB7073fd9de919443ae88e0bd2449917a65fe54898a4413ed1edcc4b67f28bce8c
README.md2.49 KBad5ff84bd7b372adf8c5ba98c83e54b547f8360b4e71cf584a4af90983784352
conds.safetensors105 KB709e5a7fa80e010a011c8244f553853aed7a49c106fff54008fbd89a0f5a6148
config.json336 Bf263efaa538f4409a2f65661bef99fb435030ff0e2dc05481d7936f2019c7f9e
ko.wav326 KB7f841587b1f264b8a3183ee7e1cf06e74d50c9ecb8711af282e9c9e8c34ca2f0
model.safetensors607 MB85fae2e4b09100e942c1c59481b8e8707916b49e58473fbe0a5cca281dbbadc4
model.safetensors.index.json356 KBf013ba172336581d1637d4b66a91d2d78385f8dc0c376965a3dd1a301722916c
models--ResembleAI--chatterbox/snapshots/05e904af2b5c7f8e482687a9d7336c5c824467d9/Cangjie5_TC.json1.92 MB7073fd9de919443ae88e0bd2449917a65fe54898a4413ed1edcc4b67f28bce8c
tokenizer.json70.0 KBdf81a7ca7c31796cbe97f7a7142d5a53b12e88e12417ebe98f66602cafaf0461
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f1d7b9696e pinned now2026-11-15 05:09 UTC10 files · 612 MB

Use it

$ fw get mlx-community/chatterbox-4bit
# manifest sha256 f2040f36128d… · 612 MB · 10 files
$ fw verify ./chatterbox-4bit mlx-community/chatterbox-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/chatterbox-4bit.json --dir ./chatterbox-4bit $ python3 fw.py verify ./chatterbox-4bit ./mlx-community__chatterbox-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/chatterbox-4bit --revision f1d7b9696e1b6242e64eb8c4a823b6d1a50425a8 --local-dir ./chatterbox-4bit

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
ad5ff84bd7b372adf8c5ba98c83e54b547f8360b4e71cf584a4af90983784352
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.speechSubject: chatterbox-4bitDate: 2026-11-15Commit: f1d7b96Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/chatterbox-4bit
Pinned commit
f1d7b9696e1b6242e64eb8c4a823b6d1a50425a8
Manifest
chatterbox-4bit.json · .minisig
Manifest sha256
f2040f36128d8c167cc0af1581b1804dadb53cf0839364a075e84456c9c52f56
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:09 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/chatterbox-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/chatterbox-4bit.json.minisig $ minisign -Vm chatterbox-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

ResembleAI/chatterbox · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/chatterbox-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. chatterbox-4bit.json. Provenance. Takedown history: none.
From: MIT <huggingface.co/MIT>Subject: ast-finetuned-audioset-10-10-0.4593
From: onnx-community <huggingface.co/onnx-community>Subject: ast-finetuned-audioset-10-10-0.4593-ONNX
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Preview-0.6b
From: Edge0 <huggingface.co/Edge0>Subject: Audio8-TTS-Realistic-Air
From: facebook <huggingface.co/facebook>Subject: audiobox-aesthetics
From: mlx-community <huggingface.co/mlx-community>Subject: chatterbox-8bit