v0.3.4
debpalash/VoiceStudiov0.3.4Jun 3, 2026by github-actions[bot]
Upgrading?
AI Summary
A fix release for Windows NVIDIA transcription failures by adding a PyTorch Whisper backend fallback when CTranslate2/cuDNN-8 libraries are missing.
Key Highlights
- Fixed 'Could not locate cudnn_ops_infer64_8.dll' on Windows.
- Added PyTorch Whisper backend as a fallback for CUDA setups.
New Features
- Windows cuDNN compatibility fix
- PyTorch Whisper backend fallback
Full Release Notes
### Fixed - **Transcription on Windows + NVIDIA failed with `Could not locate cudnn_ops_infer64_8.dll`.** WhisperX/faster-whisper need cuDNN 8 (via CTranslate2); when the side-loaded `cudnn8_compat` libs are missing, the **PyTorch Whisper** backend (Settings → Models) now works as a drop-in fallback — it builds its own transformers pipeline on PyTorch's cuDNN-9 stack, with no CTranslate2/cuDNN-8 dependency and no `OMNIVOICE_PRELOAD_TTS_ASR=1` required. (#255) ### Linux x64 artifacts ``` f339dc9f9965e68657a52f03ab482634c0a1ccdf74b23851b4ba6c03c8410088 OmniVoice Studio_0.3.4_amd64.AppImage 583ce6d798be5f811cc98c3ba765e484787f35055da692ae57cb6223e66db0dd OmniVoice Studio_0.3.4_amd64.AppImage.sig ``` ### Windows x64 artifacts ``` c19a106a0d793e1a4612663f28cfcb705721a0171da43b2eb69354c9572c4956 *OmniVoice Studio_0.3.4_x64_en-US.msi d03fdf58f810fdfcb4750e6c5e5122119e63dc649791d06313829e2f5932b936 *OmniVoice Studio_0.3.4_x64_en-US.msi.sig ```
Related Repositories
public-apis/public-apis★ 491,260
A collective list of free APIs
NousResearch/hermes-agent★ 256,129
The agent that grows with you
yt-dlp/yt-dlp★ 200,311
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,595
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,704
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.