Openai Whisper API
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
x10aix Openai Whisper API by x10aix · 84fd4f4
npx skillmds@latest add x10aix/openai-whisper-api File contents
---name: openai-whisper-apidescription: Transcribe audio via OpenAI Audio Transcriptions API (Whisper).---<role_definition>Agent for transcribing audio via the OpenAI Audio Transcriptions API using a bundled shell script.</role_definition><strategic_backbone>- Tooling: `{baseDir}/scripts/transcribe.sh` (wraps curl).- Execution Mode: Terminal execution.- Capability Scope: Cloud-based audio transcription via OpenAI's `/v1/audio/transcriptions` API.</strategic_backbone><operational_rules>- MUST ensure `OPENAI_API_KEY` is available in the environment or defined in `~/.openclaw/openclaw.json`.- MUST provide exactly one valid audio file path.- MUST use the `--out` flag if a specific destination path is required; defaults to `<input>.txt` in the same directory.- MUST use valid flags for customization: `--model` (defaults to `whisper-1`), `--language` (ISO-639-1 format), `--prompt` (for guiding spelling or speaker context), and `--json` (for full API JSON response).- AVOID transcribing files larger than the API's maximum supported size (25MB) without splitting them first.</operational_rules><process_workflow>1. Verify the `OPENAI_API_KEY` is configured.2. Determine the path to the input audio file.3. Construct the shell command with required flags: - `{baseDir}/scripts/transcribe.sh <file_path> [--model <model>] [--language <lang>] [--prompt "<context>"] [--out <output_path>] [--json]`4. Execute the command and wait for completion.</process_workflow><output_standards>- Output the absolute path to the generated transcript file.- Do not dump the full transcript in the output unless it is very short and requested by the user.</output_standards>
x10aix/Skill-Evolution/tree/main/clawdbot/openai-whisper-api commit 84fd4f4bb5
Frequently asked questions
Run npx skillmds@latest add x10aix/openai-whisper-api 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.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper). 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.