transcribe

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

Security Scan

The skill is internally consistent with its stated purpose (transcribing audio via SkillBoss) and only requires a SkillBoss API key, but it will upload local files to an external service so you should consider privacy and key scope before using it.

Purpose & Capability

Name and description match the runtime instructions: the SKILL.md shows sending base64-encoded audio to SkillBoss's /v1/pilot endpoint for STT. The single required environment variable (SKILLBOSS_API_KEY) is appropriate for a hosted STT API.

Instruction Scope

Instructions explicitly read a local file path and base64-encode it before POSTing to an external API — this is necessary for transcription, but it also means the agent can upload any file path you give it. The SKILL.md does not place limits or give privacy guidance (no mention of retention, redaction, or file-type checks), so there's a risk of unintentionally uploading sensitive content if you or an autonomous agent point it at arbitrary paths.

Install Mechanism

No install spec and no code files — instruction-only. This minimizes on-disk installation risk; nothing is downloaded or executed by an installer as part of the skill package.

Credentials

Only SKILLBOSS_API_KEY is required. That is proportional for a hosted STT service. There are no unrelated credentials or config paths requested.

Persistence & Privilege

always is false and the skill is user-invocable. Autonomous invocation is allowed by platform default but not elevated by this skill. The skill does not request modification of other skills or persistent system-wide changes.

Assessment

This skill will upload whatever local file you point it at to api.skillbossai.com using the SKILLBOSS_API_KEY. Only provide an API key you trust and limit its scope if possible. Avoid transcribing sensitive audio (legal calls, private conversations, recordings containing secrets) unless you have reviewed SkillBoss's privacy/retention policy. When using the agent, double-check file paths before invoking the skill (or restrict the agent's permissions) to prevent accidental exfiltration of non-audio or sensitive files. If you need guarantees about deletion/retention or want on-premises processing, consider a different solution or ask the skill owner for privacy details.

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"].