ClearerVoice-Studio
github.com
- Free plan
- Windows
- macOS
- Linux
- Web
- Self-hosted
What ClearerVoice-Studio is
ClearerVoice-Studio is an open-source AI speech-processing toolkit for researchers, developers and end-users. ClearVoice provides pretrained models and processing for speech enhancement, separation, super-resolution and audio-visual target-speaker extraction. Training and fine-tuning scripts are included for those tasks. SpeechScore adds intrusive and non-intrusive speech-quality assessment using metrics such as PESQ, DNSMOS, SNR and SI-SDR. The toolkit processes audio and video in batches and offers a Python interface for files, directories, .scp lists and NumPy input-output. Listed audio formats include WAV, AAC, AC3, AIFF, FLAC, M4A, MP3, OGG, OPUS, WMA and WEBM; FFmpeg is required beyond WAV codecs. Installation uses pip or the GitHub repository. Models download from Hugging Face during inference, with ModelScope as a manual alternative. Linux, macOS, Windows, self-hosted and web platforms are listed. It is released under Apache License 2.0.
Who it suits
It suits researchers, developers and end-users who need batch speech processing, model training or quality assessment.
Good to know, and what to watch
- Pretrained models cover four speech tasks
- Training and fine-tuning scripts included
- SpeechScore supplies several quality metrics
- Python accepts files and NumPy arrays
- Apache License 2.0
- FFmpeg required beyond WAV codecs
- Hugging Face demo GPU usage is limited
- Model downloads depend on external hosts
The verdict
ClearerVoice-Studio offers a broad open-source toolkit for speech transformation, extraction and evaluation. Its batch processing, Python interfaces and included models suit technical workflows, while setup and model hosting require attention.
What the maker publishes
- Additional task
- ClearVoice also provides speech super-resolution and audio-visual target speaker extraction. source
- Audio formats
- The project lists WAV, AAC, AC3, AIFF, FLAC, M4A, MP3, OGG, OPUS, WMA, and WEBM support, and says FFmpeg is required for audio codecs beyond WAV. source
- Audio formats
- The repository says ClearVoice supports formats including WAV, AAC, AC3, AIFF, FLAC, M4A, MP3, OGG, OPUS, WMA, and WEBM, and requires FFmpeg for audio codecs. source
- Demos
- The repository links to ClearVoice demos on Hugging Face and ModelScope, plus a SpeechScore demo on Hugging Face. source
- Installation
- ClearVoice can be installed with pip install clearvoice or installed from the GitHub repository. source
- Installation
- ClearVoice can be installed from PyPI with `pip install clearvoice` or installed from the GitHub repository. source
- Integration
- The README shows a Python interface that accepts audio or video file paths, directories, or `.scp` lists, and includes a NumPy input-to-output interface. source
- Intended users
- The repository describes the toolkit as designed for researchers, developers, and end-users. source
- License
- The repository includes an Apache License, Version 2.0. source
- License
- The GitHub repository identifies its license as Apache-2.0. source
- Model downloads
- Pretrained models are fetched from Hugging Face during inference, with manual downloads available from ModelScope if automatic downloads fail. source
- Model hosting
- Pretrained models are fetched from Hugging Face during inference, with ModelScope downloads offered as a manual alternative. source
- Notable limit
- The README says Hugging Face demo GPU usage is limited and ModelScope has a larger GPU usage quota. source
- Platforms
- The installation instructions describe FFmpeg setup for Ubuntu/Debian, macOS, and Windows. source
- Pretrained models
- The project provides pretrained models for enhancement, separation, super-resolution, and audio-visual target-speaker extraction. source
- Pretrained models
- The listed pretrained models cover speech enhancement, speech separation, speech super-resolution, and audio-visual target speaker extraction. source
- Purpose
- ClearerVoice-Studio is an open-source AI speech-processing toolkit for researchers, developers, and end-users. source
- Purpose
- ClearerVoice-Studio is an open-source AI speech-processing toolkit with pretrained models for speech enhancement, separation, and target speaker extraction. source
- Quality assessment
- SpeechScore is a toolkit for intrusive and non-intrusive speech-quality assessment, with metrics including PESQ, DNSMOS, SNR, and SI-SDR. source
- Quality assessment
- The included SpeechScore toolkit evaluates speech quality using metrics including SNR, PESQ, STOI, DNSMOS, and SI-SDR. source
- Speech tasks
- ClearVoice supports speech enhancement, speech separation, speech super-resolution, and audio-visual target-speaker extraction. source
- Support
- The maintainers invite questions through repository issues or email and also link to a DingTalk discussion group. source
- Support
- The maintainers invite users to raise repository issues, email the listed contacts, or join their DingTalk group. source
- Training
- The repository includes training and fine-tuning scripts for speech enhancement, separation, super-resolution, and target-speaker extraction tasks. source
Checked against the maker's pages on 9 Oct 2026.