asr-transcribe-to-text
Convert audio and video files into transcribed text with automatic speaker identification and timing markers. Choose between local processing on Apple Silicon Macs or remote API endpoints, with optional speaker diarization and plain-text fallback.
ASR Transcribe to Text converts audio and video into speaker-labeled transcripts with timestamps.
AI-generated summary based on this skill's SKILL.md
Install
daymade/claude-code-skills/asr-transcribe-to-text · repository language: Python
git clone https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-audio/asr-transcribe-to-text ~/.claude/skills/asr-transcribe-to-textnpx skillfed install daymade/claude-code-skills/asr-transcribe-to-textFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What can asr-transcribe-to-text do with my audio files?
asr-transcribe-to-text converts audio and video files into transcribed text with automatic speaker identification and timing markers. It identifies and separates speakers in a recording (diarization), generates word-level timestamps, and produces speaker-labeled text. You can process files locally on Apple Silicon Macs or use remote API endpoints, with optional plain-text fallback output.
How does asr-transcribe-to-text handle speaker diarization?
asr-transcribe-to-text automatically identifies and separates speakers in a recording through speaker diarization. This means the tool recognizes when different people are speaking and labels each segment with the speaker identity, so you can see exactly who said what in your recording without manual annotation.
Can I transcribe audio to text locally on my Apple Silicon Mac?
Yes. asr-transcribe-to-text supports local speech-to-text conversion directly on Apple Silicon Macs, eliminating the need to send audio to remote servers. This gives you privacy, offline capability, and faster processing for compatible hardware while maintaining the option to use remote API endpoints if preferred.
Does asr-transcribe-to-text add timestamps to transcriptions?
asr-transcribe-to-text generates word-level timestamps and subtitles from audio, so each word in your transcript is marked with its exact timing. This is useful for creating synchronized subtitles, navigating long recordings, and aligning text with video playback.
What audio preprocessing features does asr-transcribe-to-text offer?
asr-transcribe-to-text can preprocess and merge multi-segment audio files before transcription, preparing them for ASR (automatic speech recognition). This allows you to combine multiple audio segments into a single coherent transcript, which is especially useful for batch processing and handling fragmented recordings.
What license does asr-transcribe-to-text use?
asr-transcribe-to-text is released under the MIT license, which permits free use, modification, and distribution for both commercial and private purposes with minimal restrictions.
SKILL.md
rendered from the published skill — quoted content, verbatim
ASR Transcribe to Text
Transcribe audio/video to speaker-labeled text. Default pipeline
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 15 files
daymade-audio/asr-transcribe-to-text/.gitignore
daymade-audio/asr-transcribe-to-text/SKILL.md
daymade-audio/asr-transcribe-to-text/references/decoupled_speaker_alignment.md
daymade-audio/asr-transcribe-to-text/references/local_mlx_guide.md
daymade-audio/asr-transcribe-to-text/references/overlap_merge_strategy.md
daymade-audio/asr-transcribe-to-text/references/speaker_diarization.md
daymade-audio/asr-transcribe-to-text/references/voiceprint_speaker_id.md
daymade-audio/asr-transcribe-to-text/references/whisper_word_timestamps.md
daymade-audio/asr-transcribe-to-text/scripts/align_speakers.py
daymade-audio/asr-transcribe-to-text/scripts/diarize_speakers.py
daymade-audio/asr-transcribe-to-text/scripts/generate_audit_html.py
daymade-audio/asr-transcribe-to-text/scripts/overlap_merge_transcribe.py
daymade-audio/asr-transcribe-to-text/scripts/prepare_asr_input.py
daymade-audio/asr-transcribe-to-text/scripts/resolve_media_input.py
daymade-audio/asr-transcribe-to-text/scripts/speaker_transcribe.py