An all-in-one ASR recording-to-text skill: transcription pipeline/engine comparison, direct API integration, and SRT review templates (Hermes agent skills, verified in real-world testing in August 2026).
A guide for turning recordings into text and evaluating speech-to-text services and recording hardware. Speech-to-text, also called transcription, converts spoken audio into written words.
A set of scripts and instructions for turning recordings into text with transcription services from Google Gemini, Alibaba Bailian, or Volcengine Ark. It also supports comparing the results from these services.
A guide for testing speech-to-text systems, which turn recordings into written words, and for building batch transcription workflows. It covers comparing recording hardware, transcription services, and AI-generated meeting notes.
A workflow for turning course or meeting recordings into Chinese text. It uses audio transcription services and can produce text or timestamped segments.
A workflow for turning course or meeting transcripts in SRT files into structured study notes. SRT is a subtitle file format with timed text; the workflow cleans transcription errors and combines the transcript with existing notes.
A toolkit for comparing automatic speech recognition, or ASR, services and connecting to their APIs. ASR services convert audio into text, while the toolkit also checks audio quality, transcripts, and AI meeting summaries.
A method for evaluating speech-to-text products, meaning services that turn recordings into written text. It compares recording hardware and cloud transcription engines using controlled tests, audio measurements, and text checks.
★not rated 9 26d agoA154 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: