Skill1.3k estrellas del repoactualizado today

openai-whisper-api

This skill transcribes audio files using OpenAI's Whisper API through a bash wrapper script. Use it when you need to convert speech in audio formats like M4A or OGG to text, with options to specify language, speaker names, or output format including JSON.

Ver fuente Repositorio: trpc-agent-go

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/trpc-group/trpc-agent-go /tmp/openai-whisper-api && cp -r /tmp/openai-whisper-api/openclaw/skills/openai-whisper-api ~/.claude/skills/openai-whisper-api

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s `/v1/audio/transcriptions` endpoint.

## Quick start

```bash
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
```

Defaults:

- Model: `whisper-1`
- Output: `<input>.txt`

## Useful flags

```bash
{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 `~/.openclaw/openclaw.json`:

```json5
{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}
```

Del mismo repositorio

Demo skill that writes an output file and persists it as an artifact.

news-query-agentSubagent

Answer news queries with a fixed demo response.

weather-querySkill

Answer weather queries with a fixed demo response.

contact-lookup-agentSubagent

Look up contact phone numbers with fixed demo data.

write-okSkill

Write a deterministic OK file to out/ok.txt.