AgentSkillsCN

openai-whisper-api

使用 OpenAI 的 Whisper API 进行音频转录（基于云端，无需本地模型）。

SKILL.md
--- frontmatter
name: openai-whisper-api
description: Transcribe audio using OpenAI's Whisper API (cloud-based, no local model needed).
metadata: {"openclaw":{"emoji":"☁️","requires":{"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}}

OpenAI Whisper API

Cloud-based audio transcription via OpenAI's API.

Transcribe Audio

bash
curl -s "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1" | jq '.text'

With Timestamps

bash
curl -s "https://api.openai.com/v1/audio/transcriptions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file="@audio.mp3" \
  -F model="whisper-1" \
  -F response_format="verbose_json" \
  -F timestamp_granularities[]="segment" | jq '.segments[] | {start, end, text}'

Translate to English

bash
curl -s "https://api.openai.com/v1/audio/translations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file="@foreign-audio.mp3" \
  -F model="whisper-1" | jq '.text'