OpenAI Whisper API (curl)
SkillMediaThe openai-whisper-api skill lets an AI agent turn audio files into text transcripts by calling OpenAI's audio transcriptions endpoint through a shell script. It writes the transcript to a text or JSON file and accepts options for model, language, and prompts that carry speaker names. It needs curl and an OPENAI_API_KEY, and can point at an OpenAI-compatible proxy through OPENAI_BASE_URL.
Then ask your AI: use the OpenAI Whisper API (curl) skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Make sure curl is installed and available on the system.
What your AI can do with it
- Transcribe an audio file with the transcribe.sh script
- Write the transcript to a text file or a JSON file
- Choose the model with the --model flag, defaulting to whisper-1
- Set the spoken language with the --language flag
- Pass a --prompt with speaker names to guide the transcript
- Send requests through an OpenAI-compatible proxy via OPENAI_BASE_URL
Getting started
- Make sure curl is installed and available on the system.
- Set the OPENAI_API_KEY environment variable, or add the apiKey to the openai-whisper-api entry in the active Brigade config file.
- Optionally set OPENAI_BASE_URL to an OpenAI-compatible proxy or local gateway.
- Run the transcribe.sh script with the path to the audio file.
- Read the transcript from the output file, which defaults to the input name with a .txt extension.
What this skill tells your AI
The instructions your AI receives, as published by spinabot/brigade in skills/openai-whisper-api/SKILL.md and read by Ahel’s review.
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
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
Defaults:
- Model:
whisper-1 - Output:
<input>.txt
Useful flags
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json
API key
Set OPENAI_API_KEY, or configure it in the active Brigade config file ($BRIGADE_CONFIG_PATH, default ~/.brigade/brigade.json). Optionally set OPENAI_BASE_URL (for example http://127.0.0.1:51805/v1) to use an OpenAI-compatible proxy or local gateway:
{
skills: {
"openai-whisper-api": {
apiKey: "OPENAI_KEY_HERE",
},
},
}
Signals
- GitHub stars
- 11k
- Forks
- 70
- Last commit
- Oct 2026
Ahel review
S4info
community integration, published by spinabot, not openai
Automated review, not a security audit. Ruleset v1+k2.
Questions
- What does the skill need to run?
- It needs curl and an OPENAI_API_KEY. The key can be set as an environment variable or configured in the active Brigade config file.
- Can it use a proxy or local gateway?
- Yes. Set OPENAI_BASE_URL to an OpenAI-compatible proxy or local gateway, for example http://127.0.0.1:51805/v1.
- Which model does it use by default?
- It uses whisper-1 by default. You can change the model with the --model flag.
Advanced
- Item type
- skill
- Key
openai-whisper-api-spinabot- Source
- github.com/spinabot/brigade