← Back to Skills Marketplace
262
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xfyun-song-rec
Description
Recognize songs by singing or audio file using iFlytek's Query By ACRCloud technology.
Usage Guidance
This skill will send the provided audio file and your XF_SONG_* credentials to xfyun's API endpoint. Only install if you trust that service and are comfortable with audio and associated metadata being transmitted. Verify you supply minimal/limited credentials (rotate keys if possible), and avoid putting long-lived/privileged secrets into global envs used by other tools. Note the SKILL.md text mentions ACRCloud but the code calls xfyun — a documentation mismatch worth confirming with the publisher if you need provenance or compliance guarantees.
Capability Analysis
Type: OpenClaw Skill
Name: xfyun-song-rec
Version: 1.0.0
The skill implements song recognition using the iFlytek (XFyun) API. The Python script `scripts/index.py` correctly handles HMAC-SHA256 authentication and sends audio data to the legitimate service endpoint (`cn-east-1.api.xf-yun.com`). No evidence of data exfiltration, malicious command execution, or prompt injection was found; the code is well-structured and aligns with its stated purpose.
Capability Assessment
Purpose & Capability
Name/description (song recognition) match the code and required env vars (XF_SONG_APP_ID, XF_SONG_API_KEY, XF_SONG_API_SECRET). The script implements audio file base64 encoding and posts to an xfyun API endpoint — expected for this purpose. Minor mismatch: SKILL.md mentions 'Query By ACRCloud technology' while the code calls xfyun endpoints; this appears to be a documentation inaccuracy but not malicious.
Instruction Scope
Runtime instructions and the Python script only read the provided audio file and environment variables, build an authenticated request, and send the audio to the stated API endpoint. There are no instructions to read unrelated files, scan system state, or exfiltrate data to unexpected endpoints.
Install Mechanism
No install spec; the skill is instruction-only with an included Python script and requires python3 on PATH. No remote downloads or archive extraction are performed by an installer.
Credentials
The three required env vars are API credentials for the remote service the skill integrates with and are proportionate to the stated functionality. The script only uses those env vars and no other secrets or unrelated configuration paths.
Persistence & Privilege
The skill is not forced-always; it does not modify other skills or system-wide settings and requests no persistent elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xfyun-song-rec - After installation, invoke the skill by name or use
/xfyun-song-rec - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of song-recognition skill for iFlytek.
- Recognize songs by singing or from audio files using ACRCloud technology.
- Supports MP3 input (URL or file path), 5–30 seconds, 16kHz.
- Returns song name, artist, album, and confidence as JSON.
- Requires Python and iFlytek API credentials (3 env vars).
- Designed for music identification, discovery, and karaoke scenarios.
Metadata
Frequently Asked Questions
What is iFLYTEK Song Recognition?
Recognize songs by singing or audio file using iFlytek's Query By ACRCloud technology. It is an AI Agent Skill for Claude Code / OpenClaw, with 262 downloads so far.
How do I install iFLYTEK Song Recognition?
Run "/install xfyun-song-rec" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is iFLYTEK Song Recognition free?
Yes, iFLYTEK Song Recognition is completely free (open-source). You can download, install and use it at no cost.
Which platforms does iFLYTEK Song Recognition support?
iFLYTEK Song Recognition is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created iFLYTEK Song Recognition?
It is built and maintained by Dzy-1026 (@dzy-1026); the current version is v1.0.0.
More Skills