Transcribes audio files from URLs, stdin, or disk via Gradio endpoint using Qwen ASR.
npx skills add https://github.com/archibate/dotfiles-opencode --skill qwen-asr
Please help me install this Agent Skill. Skill: qwen-asr Source: https://github.com/archibate/dotfiles-opencode/tree/main/skills/qwen-asr Command: npx skills add https://github.com/archibate/dotfiles-opencode --skill qwen-asr
It eliminates the manual effort of listening to audio files and rewriting their contents by converting voice to readable text.
Run: uv run scripts/main.py -f audio.wav
High-intent search queries and answers about installing and using this skill.
To transcribe meeting recordings, audio speech-to-text converts wav, mp3, or ogg files into readable text. This eliminates manual listening and rewriting by generating searchable transcripts for follow-up tasks.
Speech-to-text transcription supports common audio formats including wav, mp3, and ogg. It processes audio files by uploading them to a configured Gradio endpoint and returning the text result.
Yes, a Qwen ASR Gradio demo endpoint is required to transcribe audio files. The tool uploads local files, streamed stdin audio, or remote URLs to this endpoint to receive the transcription.
Yes, speech-to-text transcription supports streaming-friendly input by reading from standard input. You can pipe streamed stdin audio directly into the tool for transcription processing.
Yes, speech-to-text transcription supports language detection with an option to specify the language manually or use auto. You can also pass optional prompt context to guide the transcription.
valtterimelkkoTranscribe audio files to text via a local Whisper service.
hmzainjamilConvert audio and video recordings into transcripts, subtitles, and meeting notes.
SriRamkunamsettyGenerate spectrograms and multi-panel feature visualizations from audio files.
papachongTranscribe audio files to text locally using the Whisper CLI.
