VocalFlow
Local TTS, voice cloning, and transcription for Windows.
Self-hosted web app powered by Qwen3-TTS and Whisper. Everything runs locally — no cloud APIs, no data leaves your machine.
Features
- Voice Cloning — clone any voice from a short audio clip, save and reuse voice prompts
- Custom Voice — 9 preset speakers with emotion and tone control
- Voice Design — create new voices from natural language descriptions
- Transcription — word-level timestamps, 6 model sizes, auto language detection
- Smart GPU — automatic model switching with VRAM cleanup, Flash Attention 2
- 10+ languages including English, Chinese, Japanese, Korean, and more
Requirements
- Windows 10/11 with a CUDA GPU (6 GB+ VRAM)
- Python 3.11 | FFmpeg
winget install ffmpeg| SoXwinget install sox
Quick Start
pip install vocalflow
vocalflow
Open http://localhost:5001 — models download automatically on first use.
From source
git clone https://github.com/0xBinayak/VocalFlow.git && cd VocalFlow
uv sync && uv run app.py
Dev mode with auto-reload: uv run gradio app.py
Contributing
Fork, uv sync, branch, ensure uvx ruff check app.py transcribe.py main.py passes, PR.
Report a bug
License
MIT | Qwen3-TTS | OpenAI Whisper | Gradio
1 maintainer
Metadata
1 maintainer
Release files for vocalflow 0.7.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| vocalflow-0.7.1.tar.gz | 67.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| vocalflow-0.7.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 81.9 kB
Release files / vocalflow-0.7.1.tar.gz
| Download URL | vocalflow-0.7.1.tar.gz |
|---|---|
| Size | 67.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4002eb5063b3b5fc7a45731b9541926d2ee87cb6b6c764305cb8ae5191a65729
|
|
BLAKE2b-256 checksum How to use checksums |
32b18875ab6ad092e9a8e9c6df710793ecc74109fd66a587768e1288dc28cae4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 23, 2026.
Transparency logRelease files / vocalflow-0.7.1-py3-none-any.whl
| Download URL | vocalflow-0.7.1-py3-none-any.whl |
|---|---|
| Size | 14.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e543a53dcaadc20faea34b3b30028509331e593a5f9d49e2036ed5fc23e56aa5
|
|
BLAKE2b-256 checksum How to use checksums |
7984dc6091a55b2c158cf237559d9daf8ed5de253fd3be2d98a4127130c254e3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 23, 2026.
Transparency log
