Transcribe audio to text using OpenAI Whisper models locally or via cloud API.
npx skills add https://github.com/rkz91/coco --skill openai-whisper-rkz91
Please help me install this Agent Skill. Skill: openai-whisper Source: https://github.com/rkz91/coco/tree/main/skills/openai-whisper Command: npx skills add https://github.com/rkz91/coco --skill openai-whisper-rkz91
Transcribing audio to text is a common bottleneck in research, media, and product workflows, where long recordings must be converted into searchable, editable transcripts.
Transcribe a local audio file with Whisper to generate a text transcript on your device.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio to text locally using the on-device CLI mode of OpenAI Whisper, which enables offline transcription without requiring an API key. This preserves privacy and reduces latency for your private workflow.
Batch transcribing large audio datasets is best handled using the cloud API mode for speech-to-text. This mode provides fast processing with optional translation and language hints, requiring an OPENAI_API_KEY for access.
On-device audio transcription works completely offline without an internet connection. The local CLI mode operates independently using Whisper models, ensuring privacy and eliminating network latency during speech-to-text processing.
You can convert interview recordings into searchable text transcripts using Whisper speech-to-text. Both local and cloud modes process long recordings, generating accurate transcripts suitable for notes, summaries, or data extraction.
An OpenAI API key is only required for speech-to-text transcription in cloud API mode. Local on-device transcription operates without any API key, relying solely on downloaded Whisper models for offline processing.
Cloud API speech-to-text differs from on-device transcription by offering fast batch processing for large datasets with optional translation, while on-device mode prioritizes offline privacy and lower latency without requiring an API key.
Yogi-076Transcribe audio files to text via OpenAI's Whisper transcription endpoint.
math-incExtract YouTube transcripts and convert them into JSON or text formats.
bomberoxenviosdosruedasBuild speech transcription pipelines using Whisper models and cloud ASR services.
steipeteTranscribe local audio files to text or subtitles using the Whisper CLI.
