transcribe

Speech-to-text via SkillBoss API Hub (STT, powered by Whisper and more).

Security Scan

The skill is internally consistent: it sends audio to SkillBoss API for transcription and only requires a single SKILLBOSS_API_KEY environment variable, with no install steps or unrelated permissions requested.

Purpose & Capability

The skill's description (transcribe via SkillBoss) matches the runtime instructions which call https://api.skillbossai.com/v1/pilot. Minor inconsistency: SKILL.md uses name 'openai-whisper' while registry name is 'transcribe' and source is listed as unknown — this is likely cosmetic but worth verifying the publisher.

Instruction Scope

Instructions show reading a local audio file, base64-encoding it, and POSTing it to api.skillbossai.com with the SKILLBOSS_API_KEY. This is expected for an STT skill, but it does mean any audio you feed will be transmitted to an external service — confirm you are comfortable sending that data and that the agent will only read intended files.

Install Mechanism

No install spec and no code files (instruction-only). This minimizes local persistence and disk writes.

Credentials

Only SKILLBOSS_API_KEY is required, which is proportionate to calling a third-party API. No other unrelated secrets or config paths are requested.

Persistence & Privilege

always is false and the skill does not request elevated or persistent platform privileges. It does allow normal autonomous invocation (platform default).

Assessment

This skill will transmit any audio you provide to api.skillbossai.com using the SKILLBOSS_API_KEY. Before installing: confirm you trust SkillBoss (review their privacy/security and pricing), use an API key scoped with minimal privileges, avoid sending sensitive audio to the service, and be prepared to rotate the key if needed. Also verify the publisher (registry owner and homepage) since the SKILL.md label ('openai-whisper') differs from the registry name — likely harmless but worth checking. Finally, ensure the agent is only given the specific audio files you intend to transcribe.

Whisper STT via SkillBoss API Hub

Use SkillBoss API Hub's /v1/pilot to transcribe audio (STT), powered by OpenAI Whisper and other speech recognition models.

Quick start (Python)

import requests, base64, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.skillbossai.com/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
        timeout=60,
    )
    return r.json()

# Transcribe audio file
audio_b64 = base64.b64encode(open("/path/audio.mp3", "rb").read()).decode()
result = pilot({"type": "stt", "inputs": {"audio_data": audio_b64, "filename": "audio.mp3"}})
text = result["result"]["text"]
print(text)

# Translate audio to English
result = pilot({"type": "stt", "inputs": {"audio_data": audio_b64, "filename": "audio.m4a", "task": "translate"}})
text = result["result"]["text"]
print(text)

Notes

• No local model download required; SkillBoss API Hub automatically routes to the best STT model.
• SKILLBOSS_API_KEY environment variable required.
• Response text is at result["result"]["text"].