sh.edict/edict Model Context Protocol (MCP) Server
The sh.edict/edict MCP server provides functionality to search dictation transcripts and to transcribe audio or video on-device, producing outputs that include speaker labels. Its scope is centered on working with dictation and media inputs without relying on external transcription services.
🛠️ Key Features
- Search dictation transcripts
- Transcribe audio or video
- On-device transcription
- Speaker labels in transcription results
🚀 Use Cases
- Find information across dictation transcripts
- Convert audio/video recordings into labeled transcript text
- Distinguish speakers within transcribed media
⚡ Developer Benefits
- Enables transcript search workflows
- Supports labeled outputs suitable for downstream processing
⚠️ Limitations
- Specific tool interfaces and constraints are not provided in the available source data.