x10aix Openai Whisper by x10aix · dca31cb
npx skillmds@latest add x10aix/openai-whisper File contents
---name: openai-whisperdescription: Local speech-to-text with the Whisper CLI (no API key).---<role_definition>Agent for performing local speech-to-text transcription and translation using the OpenAI Whisper CLI.</role_definition><strategic_backbone>- Tooling: `whisper` CLI.- Execution Mode: Terminal execution.- Capability Scope: Local, offline audio transcription and translation into various formats (txt, srt, etc.).</strategic_backbone><operational_rules>- MUST provide exactly one valid input audio file path.- MUST specify the target `--model` (e.g., `tiny`, `base`, `small`, `medium`, `large`, `turbo`). If omitted, defaults to `turbo`.- MUST expect and allow the model to download to `~/.cache/whisper` on the first run.- MUST use `--task translate` if the goal is to transcribe non-English audio into English text.- MUST specify `--output_format` (e.g., `txt`, `srt`, `vtt`) and `--output_dir`.- AVOID running large models if system resources are constrained or if speed is prioritized.</operational_rules><process_workflow>1. Identify the absolute path to the audio file.2. Determine the appropriate model size, task (transcribe or translate), and desired output format.3. Construct the execution command: - `whisper <audio_path> --model <model> --output_format <format> --output_dir <dir> [--task translate]`4. Execute the command and wait for completion.</process_workflow><output_standards>- Output the exact path to the generated transcript file.- Do not attempt to summarize massive transcripts in the output unless specifically requested; point the user to the file.</output_standards>
x10aix/Skill-Evolution/tree/main/clawdbot/openai-whisper commit dca31cbe71
Frequently asked questions
Run npx skillmds@latest add x10aix/openai-whisper in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Local speech-to-text with the Whisper CLI (no API key). It is listed under Integrations & APIs on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
x10aix (@x10aix) published this skill. Their other Agent Skills are listed on their SkillMD profile.