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
Decision gist · record as of 2026-07-27
ASR Transcribe to Text converts audio and video into speaker-labeled transcripts with timestamps. 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.
Use it when
- asr-transcribe-to-text automatically identifies and separates speakers in a recording through speaker diarization.
- Yes.
Verify before relying
Read SKILL.md below before installing (19 files). Open directory: indexed for reading, not audited.
Install
daymade/claude-code-skills/asr-transcribe-to-text · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently 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)
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
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Transcribe audio or video to speaker-labeled text with timestamps”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Convert interview recordings into searchable transcripts with word-level timestamps and speaker identification. Extract and verify quotes for publication, track sources, and organize multi-interview projects with built-in templates for manual transcription and quote management.
Convert local audio and video files into text transcripts using Whisper, then optionally generate meeting minutes, action items, speaker-separated output, and presentation-ready summaries. Supports Japanese meetings, Teams recordings, and other media formats entirely on your machine.
Media Transcription runs a durable, event-driven pipeline to transcribe meeting media stored on the NAS, using MLX Whisper for speech recognition and pyannote for speaker identification. Monitor progress in real time, cancel runs, or resume from partial completions—all orchestrated through Inngest with detached local inference processes that prevent timeout failures. Execution is limited to the Flagg host worker with direct access to the media mount.
Faster-whisper delivers rapid, offline speech-to-text transcription using CTranslate2, achieving 4-6x speed over OpenAI Whisper while maintaining identical accuracy. Generate subtitles in multiple formats (SRT, VTT, TTML, CSV), identify speakers, process batches with ETA, search transcripts, and detect chapters—all without API dependencies.
Transcription Automation handles speech-to-text conversion for audio files, video recordings, and live streams, automatically identifying speakers and generating formatted transcripts. The skill produces searchable archives, meeting notes with action items, and subtitles in SRT or VTT formats across multiple languages. It integrates with platforms like Zoom, YouTube, and podcasting workflows to streamline content processing end-to-end.
Whisper is OpenAI's multilingual speech recognition model for converting audio and video into text across 99 languages. It handles noisy recordings, supports translation to English, and offers multiple model sizes from lightweight to high-accuracy variants. Use it for podcasts, meeting transcription, video subtitles, and multilingual audio processing.
More skills Funasr Transcribe (unlicensed) · byted-las-audio-convert (Apache-2.0)