VibeVoiceFusion
Full-stack multi-speaker voice generation web system with LoRA fine-tuning and VRAM optimization
GraphCanon updated 3w · GitHub synced 3w
Decision brief
VibeVoiceFusion is a full-stack Python-based system for multi-speaker voice generation that incorporates LoRA fine-tuning for efficiency and VRAM optimization, derived from Microsoft's VibeVoice architecture.
Good fit when
- - You require multi-speaker voice synthesis with support for batch processing and efficient model tuning using LoRA
- - The project needs to run optimally on systems with lower VRAM capacities
Avoid when
- - Your project requires real-time voice generation without prioritizing VRAM efficiency or speaker diversity
- - You're working in an environment where Python is not preferred for development
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (151d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install VibeVoiceFusionSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
VibeVoiceFusion is a Python-based project that offers full-stack capabilities for generating voices from multiple speakers. It utilizes LoRA (Low-Rank Adaptation) for efficient model fine-tuning, supports batch processing, and includes mechanisms to optimize VRAM usage.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Jul 25, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Jul 25, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 25, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 25, 2026)
# Install Python packageSource link
Tags
README
Installation
Option 1: Docker (Recommended for Production)
Build docker image
---
# Build and the docker image
docker compose build vibevoice
After build successfully, run command:
docker run -d \
--name vibevoicefusion \
--gpus all \
-p 9527:9527 \
-v $(pwd)/workspace:/workspace/zhao-kun/vibevoice/workspace \
zhaokundev/vibevoicefusion:latest
Access the application at http://localhost:9527
The Docker image is available on Docker Hub, and you can launch VibeVoiceFusion using the following command.
docker pull zhaokundev/vibevoicefusion
docker run -d \
--name vibevoicefusion \
--gpus all \
-p 9527:9527 \
-v $(pwd)/workspace:/workspace/zhao-kun/vibevoice/workspace \
zhaokundev/vibevoicefusion:latest
Build Time: 18-28 minutes | Image Size: ~12-15GB
Option 2: Manual Installation
1. Install Backend Dependencies
---
# Install Python package
pip install -e .
2. Download Pre-trained Model
Download from HuggingFace (choose one):
- Float8 (Recommended): vibevoice7b_float8_e4m3fn.safetensors (~7GB) (Supported by RTX 40 series and above graphics cards.)
- BFloat16 (Full Precision): vibevoice7b_bf16.safetensors (~14GB)
- Config: config.json
Place files in ./models/vibevoice/
3. Install Frontend Dependencies (for development)
cd frontend
npm install
4. Build Frontend (for production)
cd frontend
npm run build
cp -r out/* ../backend/dist/
License
This project follows the same license terms as the original Microsoft VibeVoice repository. Please refer to the LICENSE file for details.
For agents
This page has a .md twin and JSON over the API.