vocalflow 0.7.1

Local TTS and audio transcription web app

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  |  SoX winget 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