Merge pull request #15846 from phonology024/add-babelscribe

Add babelscribe — local speech-to-text on any GPU 🤖🤖🤖
This commit is contained in:
Frank Fiegel
2026-10-23 09:17:53 -07:00
committed by GitHub
+1
View File
@@ -4481,6 +4481,7 @@ Translation tools and services to enable AI assistants to translate content betw
- [eviscerations/whisper-windows-mcp](https://github.com/eviscerations/whisper-windows-mcp) [![eviscerations/whisper-windows-mcp MCP server](https://glama.ai/mcp/servers/eviscerations/whisper-windows-mcp/badges/score.svg)](https://glama.ai/mcp/servers/eviscerations/whisper-windows-mcp) 📇 🏠 🪟 - Local audio and video transcription on Windows using whisper.cpp with Vulkan GPU acceleration: batch processing, multilingual support and background jobs.
- [ankurmans/pepys-mcp](https://github.com/ankurmans/pepys-mcp) [![ankurmans/pepys-mcp MCP server](https://glama.ai/mcp/servers/ankurmans/pepys-mcp/badges/score.svg)](https://glama.ai/mcp/servers/ankurmans/pepys-mcp) 📇 ☁️ 🏠 - Transcribe audio, video, YouTube links and podcast feeds via Pepys, with speaker diarization, SRT/VTT export and transcript search.
- [phonology024/babelscribe](https://github.com/phonology024/babelscribe) [![phonology024/babelscribe MCP server](https://glama.ai/mcp/servers/phonology024/babelscribe/badges/score.svg)](https://glama.ai/mcp/servers/phonology024/babelscribe) 🐍 🏠 🍎 🪟 🐧 - Local speech-to-text and SRT/VTT subtitles for audio and video in 99 languages on your own AMD, NVIDIA, Intel or Apple GPU (whisper.cpp via Vulkan/CUDA/Metal), with an accurate mode using Thai and Hindi fine-tunes.
- [spokenmd/spoken](https://github.com/spokenmd/spoken) [![spokenmd/spoken MCP server](https://glama.ai/mcp/servers/spokenmd/spoken/badges/score.svg)](https://glama.ai/mcp/servers/spokenmd/spoken) 📇 ☁️ - Search podcast episodes and fetch published transcripts as Markdown with real speaker names via the Spoken API.
### 🎧 <a name="text-to-speech"></a>Text-to-Speech