Transcribe audio files into text transcripts with optional speaker diarization.
npx skills add https://github.com/bl1nk-bot/skills-cli --skill transcribe-bl1nk-bot
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/bl1nk-bot/skills-cli/tree/main/skills/transcribe Command: npx skills add https://github.com/bl1nk-bot/skills-cli --skill transcribe-bl1nk-bot
Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.
Run the bundled transcribe CLI on an audio file to generate a transcript and optionally diarize speakers.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio and label speakers by running the bundled CLI with optional diarization and known-speaker hints. The workflow uses OpenAI to convert audio into accurate text transcripts suitable for meetings and interviews.
Yes, the transcription CLI supports known-speaker references to help identify and label participants accurately. This feature is applicable for interviews and meetings where distinguishing speakers is required.
The bundled transcribe CLI provides a deterministic workflow for automated speech-to-text pipelines. It handles model selection, chunking strategy, and output control, saving transcripts by default under a configurable output directory.
Yes, the tool relies on OpenAI for speech-to-text processing and requires an API key. The CLI workflow includes safe handling of API keys and known-speaker references to securely generate text transcripts.
The CLI workflow satisfies requirements for response formats, chunking strategy, and output control. Transcripts are saved by default under output/transcribe/, and the output directory is configurable via CLI arguments.
The CLI supports language hints and model selection for converting audio into text transcripts. It is applicable for multimedia archives where accurate transcripts and speaker labeling are required.
storyclaw-officialGenerate speech audio from text using the OpenAI Audio API.
M1AlbertTranscribe audio to text with optional speaker diarization.
letta-aiTranscribe audio files to text or JSON via the OpenAI Whisper API.
eachlabsConvert text to speech and transcribe audio with speaker diarization.
