Transcribe audio and video files using configurable speech recognition backends.
npx skills add https://github.com/swyxio/skills --skill transcribe-anything
Please help me install this Agent Skill. Skill: transcribe-anything Source: https://github.com/swyxio/skills/tree/main/transcribe-anything Command: npx skills add https://github.com/swyxio/skills --skill transcribe-anything
Manually transcribing audio and video content is slow, expensive, and error-prone, especially for long recordings, files with poor audio quality, or content that requires speaker identification. This skill automates the full transcription workflow from raw media to polished, formatted text.
Use the transcribe-anything skill to generate a formatted markdown transcript with speaker labels for the attached 1-hour team meeting recording.
High-intent search queries and answers about installing and using this skill.
To transcribe long podcast audio, this skill automatically preprocesses files, skips silence, and chunks uploads to prevent hallucination cascades and meet API size limits for recordings up to 8+ hours.
Generating SRT subtitles from video files is handled by configuring one of 9+ supported ASR backends, which processes the audio track and flexibly exports timestamped subtitle formats alongside plain text and markdown.
Speaker diarization for meeting transcription is supported through configurable ASR backends like WhisperX, allowing you to generate formatted markdown transcripts with distinct speaker labels.
Whisper can be used for local speech-to-text processing as one of the 9+ available ASR backends, letting you balance speed, accuracy, cost, and diarization needs without requiring external cloud services.
Audio transcription hallucinations on long media files occur when continuous processing cascades errors; this skill mitigates this by applying audio preprocessing, silence detection, and chunked processing.
You can convert audio and video files of varying lengths to accurate text output, extracting multi-format transcripts including timestamped markdown, JSON with word-level timestamps, SRT, VTT, or plain text.
CC90210Automates video production pipeline from raw footage to platform-ready exports.
qhkmFetch web pages and convert them into clean, readable text.
0xslineAutomate ASR transcription, captioning, and subtitle management for video and audio assets.
imMamdouhaboammarDesign speech transcription pipelines with local Whisper and cloud ASR services.
