← 返回 Skills 市场
364
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install aiml-voice
功能描述
Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script...
使用说明 (SKILL.md)
AIMLAPI Voice Transcription
Overview
A robust skill for transcribing audio via AIMLAPI's specialized speech-to-text endpoints. It handles queuing, polling for results, and automatic MIME-type detection.
Quick Start
# Set your API key first (if not in env)
# export AIMLAPI_API_KEY="your-key-here"
# Transcribe a file
python {baseDir}/scripts/transcribe.py path/to/audio.ogg
Tasks
Process Voice Messages
When an audio file is received, use this script to extract the text.
python {baseDir}/scripts/transcribe.py \x3Cfile_path> \
--model "#g1_whisper-medium" \
--verbose
Arguments
file: (Required) Path to the audio file.--model: Model ID (default:#g1_whisper-medium).--out: Path to save the transcript text.--poll-interval: Seconds between status checks (default: 5).--max-wait: Stop waiting after N seconds (default: 300).
Dependencies
- Python 3
AIMLAPI_API_KEYset in environment or provided via--apikey-file.
安全使用建议
This skill appears to do what it claims: it uploads a local audio file to https://api.aimlapi.com for transcription and returns the transcript. Before installing, verify you trust the AIMLAPI service and the key you will provide (the API key can be used for billing and data access). Note the source/publisher is unknown and there is no homepage — if you require strong provenance, request a trustworthy publisher or review provenance. Also be aware the script reads the entire audio file into memory (no size checks), so avoid processing very large files or sensitive recordings until you confirm the service's privacy policy. Test with non-sensitive audio first and keep your AIMLAPI_API_KEY secret.
功能分析
Type: OpenClaw Skill
Name: aiml-voice
Version: 1.0.0
The skill is designed for transcribing audio files using the AIMLAPI service. The `SKILL.md` provides clear, non-malicious instructions for the AI agent, specifying the use of the `transcribe.py` script with relevant arguments. The `transcribe.py` script correctly implements this functionality, handling API keys from environment variables or a specified file, performing network requests only to the hardcoded `api.aimlapi.com` endpoint, and processing local audio files. There is no evidence of intentional harmful behavior such as data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection attempts against the agent.
能力评估
Purpose & Capability
Name/description match the included script and declared env var: the tool uploads audio to AIMLAPI STT endpoints and polls for results. Requiring AIMLAPI_API_KEY and python is proportional.
Instruction Scope
SKILL.md tells the agent to run the provided transcribe.py script and mentions only the API key and usual args. The instructions do not request unrelated files, extra credentials, or external endpoints beyond the AIMLAPI API.
Install Mechanism
No install spec is present (instruction-only plus a bundled script). The script uses only Python standard libraries and no external downloads, so there is no high-risk installer activity.
Credentials
Only AIMLAPI_API_KEY is required, which is appropriate for a third-party STT service. Note: the API key grants access to your AIMLAPI account and usage/billing, so treat it like a secret and only provide a key you trust the service with.
Persistence & Privilege
always is false and the skill does not request persistent system-level configuration or modify other skills. It does not ask to run continuously or store credentials beyond reading env or an explicit apikey file.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install aiml-voice - 安装完成后，直接呼叫该 Skill 的名称或使用
/aiml-voice触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of AIMLAPI audio transcription skill.
- Transcribes audio files (ogg, mp3, wav, etc.) using AIMLAPI's speech-to-text endpoints.
- Supports robust queuing, polling for results, and automatic MIME-type detection.
- CLI script for submitting, tracking, and saving transcription output.
- Requires AIMLAPI_API_KEY.
- Adjustable model, polling interval, and timeout options.
元数据
常见问题
AIML Voice Transcript 是什么？
Transcribe audio files (ogg, mp3, wav, etc.) using AIMLAPI. Use when the user provides audio messages or local audio files. Provides a reliable Python script... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 364 次。
如何安装 AIML Voice Transcript？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aiml-voice」即可一键安装，无需额外配置。
AIML Voice Transcript 是免费的吗？
是的，AIML Voice Transcript 完全免费（开源免费），可自由下载、安装和使用。
AIML Voice Transcript 支持哪些平台？
AIML Voice Transcript 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 AIML Voice Transcript？
由 AI/ML API（@aimlapihello）开发并维护，当前版本 v1.0.0。
推荐 Skills