Agent Skills › the-open-agent/openagent › openai-whisper-api

openai-whisper-api

GitHub

通过 OpenAI Whisper API 转录音频文件，支持指定语言、说话人提示及自定义基础 URL，适用于语音转文本场景。

skills/openai-whisper-api/SKILL.md the-open-agent/openagent

Trigger Scenarios

用户需要转录音频文件需要将语音转换为文本

Install

npx skills add the-open-agent/openagent --skill openai-whisper-api -g -y

More Options

Use without installing

npx skills use the-open-agent/openagent@openai-whisper-api

指定 Agent (Claude Code)

npx skills add the-open-agent/openagent --skill openai-whisper-api -a claude-code -g -y

安装 repo 全部 skill

npx skills add the-open-agent/openagent --all -g -y

预览 repo 内 skill

npx skills add the-open-agent/openagent --list

SKILL.md

Frontmatter

{
    "name": "openai-whisper-api",
    "homepage": "https:\/\/platform.openai.com\/docs\/guides\/speech-to-text",
    "metadata": {
        "emoji": "🌐",
        "requires": {
            "env": [
                "OPENAI_API_KEY"
            ],
            "bins": [
                "curl"
            ]
        },
        "primaryEnv": "OPENAI_API_KEY"
    },
    "description": "Transcribe audio via OpenAI Audio Transcriptions API (Whisper)."
}

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI's /v1/audio/transcriptions endpoint. Set OPENAI_BASE_URL to use an OpenAI-compatible proxy or local gateway.

Quick start

curl -sS "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@/path/to/audio.m4a" \
  -F "model=whisper-1" \
  -F "response_format=text" \
  > transcript.txt

Defaults:

Model: whisper-1
Output format: text

Options

# With language hint
curl -sS "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@audio.ogg" \
  -F "model=whisper-1" \
  -F "response_format=text" \
  -F "language=en" \
  > transcript.txt

# With speaker hint (prompt)
curl -sS "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@audio.m4a" \
  -F "model=whisper-1" \
  -F "response_format=text" \
  -F "prompt=Speaker names: Peter, Daniel" \
  > transcript.txt

# JSON output
curl -sS "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@audio.m4a" \
  -F "model=whisper-1" \
  -F "response_format=json" \
  > transcript.json

Custom base URL

Set OPENAI_BASE_URL to use an OpenAI-compatible proxy or local gateway:

API_BASE="${OPENAI_BASE_URL:-https://api.openai.com/v1}"
curl -sS "${API_BASE}/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "file=@audio.m4a" \
  -F "model=whisper-1" \
  -F "response_format=text" \
  > transcript.txt