OpenBMB/VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #38 of 2,503 repositories GStars tracks this week (top 2%).
No releases in the last 90 days; the most recent was 154 days ago, with 28 contributors on GitHub.
Peaked at #5 in the weekly ranking the week of Jan 18, its best in the past year.
Use Cases & Benefits
- Implements a tokenizer-free text-to-speech system that generates context-aware, expressive, and natural multilingual speech using continuous speech representations.
- Enables true-to-life zero-shot voice cloning and expressive speech synthesis with high efficiency and real-time streaming on consumer GPUs.
- Use for creating personalized voice models by fine-tuning on custom datasets with full or LoRA fine-tuning support.
- Use for generating expressive multilingual speech in applications requiring natural prosody and style adaptation from text input.
- Use for real-time streaming TTS in interactive voice assistants or live broadcasting with low latency and high audio quality.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
👋 Contact us on WeChat
VoxCPM is a novel tokenizer-free Text-to-Speech (TTS) system that redefines realism in speech synthesis. By modeling speech in a continuous space, it overcomes the limitations of discrete tokenization and enables two flagship capabilities: context-aware speech generation and true-to-life zero-shot voice cloning.
Unlike mainstream approaches that convert speech to discrete tokens, VoxCPM uses an end-to-end diffusion autoregressive architecture that directly generates continuous speech representations from text. Built on MiniCPM-4 backbone, it achieves implicit semantic-acoustic decoupling through hierachical language modeling and FSQ constraints, greatly enhancing both expressiveness and generation stability.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+5,014 stars over 80 days across 10 snapshot days; best day +183 on Sep 16.
Forks
4.4K+529
Open issues
127+30
Compared with peers in Machine Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| openbq-org/OpenBB | 74.2K | +0 | 75 | 14 days ago |
| CorentinJ/Real-Time-Voice-Cloning | 60.2K | +0 | 75 | — |
| apache/airflow | 47.2K | +0 | 75 | 27 days ago |
| OpenBMB/VoxCPM | 39.2K | +0 | 34 | 154 days ago |
| nautechsystems/nautilus_trader | 29.9K | +0 | 75 | 7 days ago |
| GeeeekExplorer/nano-vllm | 15.8K | +0 | 75 | — |
| Category median | 47.2K | +0 | 75 | — |
Also by OpenBMB
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description