videopython-chatterbox
Chatterbox TTS by Resemble AI, republished with corrected dependency metadata.
Version 0.1.7.post2 also fixes short-text alignment: repetition detection now checks that earlier text tokens exist before reducing their attention scores. Inputs with five or fewer text tokens retain long-tail and token-repetition EOS checks without raising an empty-reduction error. The distribution-name lookup and corrected dependency metadata remain the other changes from upstream 0.1.7.
pip install videopython-chatterbox
The import name is unchanged, so this is a drop-in replacement:
from chatterbox.mtl_tts import ChatterboxMultilingualTTS
Conflict warning: this package and
chatterbox-ttsboth install a top-levelchatterboxpackage. Install one or the other, never both.
Why this fork exists
Upstream chatterbox-tts 0.1.7 pins diffusers==0.29.0, torch==2.6.0,
torchaudio==2.6.0, transformers==5.2.0 and safetensors==0.5.3. Those ==
pins make it unsatisfiable alongside any modern ML stack — for example
pyannote-audio>=4.0 requires torch>=2.8.0, so the two cannot coexist:
$ pip install chatterbox-tts diffusers>=0.35.0
× No solution found: chatterbox-tts==0.1.7 depends on diffusers==0.29.0
The pins are not load-bearing. Chatterbox touches diffusers in exactly one
place — its vendored Matcha-TTS decoder — importing 9 symbols (GEGLU, GELU,
AdaLayerNorm, AdaLayerNormZero, ApproximateGELU, Attention,
LoRACompatibleLinear, maybe_allow_in_graph, get_activation). All of them
still exist and behave identically in diffusers 0.39.
Verification
Real synthesis and voice cloning were run on
torch 2.13.0 / diffusers 0.39.0 / transformers 5.14.1 / numpy 2.4.6, then
repeated under upstream's pinned transformers==5.2.0, with fixed seeds:
| seed | samples | identical | max abs diff |
|---|---|---|---|
| 1234 | 91200 | yes | 0.0 |
| 1235 | 86400 | yes | 0.0 |
| 1236 | 144000 | yes | 0.0 |
Output is bit-identical. Generations were also transcribed with Whisper to confirm the audio matches the requested text, rather than merely being non-silent.
Metadata changes
| dependency | upstream 0.1.7 | here | why |
|---|---|---|---|
numpy |
<2.0.0 (py<3.13) |
>=1.24.0 |
verified on 2.4.6 |
librosa |
==0.11.0 |
>=0.11.0 |
0.11.0 is still latest |
torch |
==2.6.0 |
>=2.6.0 |
verified on 2.13.0 |
torchaudio |
==2.6.0 |
>=2.6.0 |
follows torch |
transformers |
==5.2.0 |
>=5.2.0 |
verified bit-identical on 5.14.1 |
diffusers |
==0.29.0 |
>=0.29.0,<1.0 |
verified on 0.39.0; see cap below |
conformer |
==0.3.2 |
>=0.3.2 |
0.3.2 is still latest |
safetensors |
==0.5.3 |
>=0.5.3 |
verified on 0.8.0 |
pykakasi |
==2.3.0 |
>=2.3.0 |
2.3.0 is still latest |
gradio |
==6.8.0 |
removed | not imported anywhere in the package |
setuptools |
undeclared | <81 |
see below |
Two of these are deliberate constraints rather than relaxations:
diffusers<1.0 — LoRACompatibleLinear is deprecated with removal
scheduled for diffusers 1.0.0. It is the one symbol that will genuinely break,
so the cap is real.
setuptools<81 — resemble-perth declares no dependencies at all and
imports pkg_resources, which setuptools removed in 82+. Its __init__.py
swallows the resulting ImportError and sets PerthImplicitWatermarker = None,
so chatterbox fails later at model load with a confusing
TypeError: 'NoneType' object is not callable. Upstream is affected by this
too; it is simply undeclared there.
Relationship to upstream
Changes are limited to packaging compatibility and the documented short-text
alignment crash fix. If upstream incorporates these fixes and relaxes its pins,
prefer chatterbox-tts.
To rebase onto a new upstream release: replace src/chatterbox/ wholesale,
re-apply the distribution-name lookup in chatterbox/__init__.py, and check
whether the short-text alignment fix is already present before carrying it forward.
Run python -m pytest tests/test_short_alignment.py, verify the remaining source
against the new sdist, bump version to <upstream>.postN, and re-check the
dependency table above.
For 0.1.7.post2, all seven direct PyTorch tests pass (text widths 1–6 and 20). GPU synthesis of “za”, “Ja” and a full Polish sentence also succeeded without videopython's alignment monkeypatch. These checks cover the short-input crash; they do not establish general speech quality or performance.
License
MIT, Copyright (c) 2025 Resemble AI — preserved verbatim in LICENSE. See NOTICE for the fork's provenance statement. Model weights are not redistributed; they are fetched at runtime from the Hugging Face Hub.
Metadata
Release files for videopython-chatterbox 0.1.7.post2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| videopython_chatterbox-0.1.7.post2.tar.gz | 75.1 kB | Without provenance | Details for videopython_chatterbox-0.1.7.post2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| videopython_chatterbox-0.1.7.post2-py3-none-any.whl | Python 3 | none | any | Details for videopython_chatterbox-0.1.7.post2-py3-none-any.whl |
Total release size: 183.0 kB
Release files / videopython_chatterbox-0.1.7.post2.tar.gz
| Download URL | videopython_chatterbox-0.1.7.post2.tar.gz |
|---|---|
| Size | 75.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4d2a5221cbe407ffbe0b369c57b340fd6bc1958092d923b4756cdfc50835a56b
|
|
BLAKE2b-256 checksum How to use checksums |
6498cfc94fb87ef600e06c31ba9865b1cd56692bf39e0fa65cc85f3ca8e5680b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.10 {"installer":{"name":"uv","version":"0.9.10"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / videopython_chatterbox-0.1.7.post2-py3-none-any.whl
| Download URL | videopython_chatterbox-0.1.7.post2-py3-none-any.whl |
|---|---|
| Size | 107.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
df9d37fcd637b67ac67670ef23c976b180b6de7bc158017a136130aa95a11db8
|
|
BLAKE2b-256 checksum How to use checksums |
4837ad055353e911a502a3251bdbc31452fcc537fcab91bd9c621ace7dadaba1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.10 {"installer":{"name":"uv","version":"0.9.10"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for videopython-chatterbox 0.1.7.post2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.