kie-audioGenerate music and audio via Kie.ai's Suno gateway (V3.5 through V5.5). Use for background tracks, instrumental beds, full songs with vocals, or extending ex...
Install via ClawdBot CLI:
clawdbot install benhuebner01/kie-audioGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/original.mp3Audited Apr 28, 2026 · audit v1.0
Generated Oct 6, 2026
A YouTuber needs royalty-free background tracks for videos without hiring a composer. They run the skill with an instrumental prompt specifying genre, mood, and duration, then download the generated tracks as MP3 files for editing. This eliminates licensing headaches and speeds up content production.
An indie game developer generates multiple instrumental loops for different levels (menu, action, ambient) to test mood and pacing during development. The skill's ability to extend existing audio helps build longer tracks from short prototypes. Final tracks are later refined or replaced based on playtesting feedback.
A podcaster uses the skill to create a catchy intro and outro with vocals or instruments, matching their show's theme. The `--custom-mode` flag allows lyric-driven generation for branded audio. The downloaded variations provide options to A/B test audience response.
A small marketing agency generates short, upbeat songs with vocals for social media advertisements (TikTok, Instagram Reels). They use the `--prompt` to embed campaign-specific lyrics and the `--extend` feature to build longer versions from a 15-second hook. This reduces reliance on stock music libraries.
A wellness app developer uses the skill to generate ambient, instrumental tracks for meditation and sleep features. Prompts specify calming genres like lo-fi or nature sounds, and the multi-track output allows curating a rotating playlist. Tracks are downloaded and hosted within the app's backend.
The core skill is free with a limited number of generations per day, while a premium tier unlocks higher-quality models (V5_5), faster processing, and extended audio capabilities. Users pay a monthly subscription to remove limits and access priority support. This model attracts casual users and monetizes power users.
Developers integrate the skill into their own applications via an API endpoint and are charged per successful generation. Pricing varies by model complexity (e.g., V5_5 costs more than V3_5) and whether vocals are included. This model is ideal for platforms that need on-demand music generation without maintaining infrastructure.
Large companies (e.g., media production houses, game studios) license the skill's underlying technology to integrate into their internal tools or products. They pay an annual license fee plus support and customization services. This model provides stable, high-value revenue and reduces direct competition.
💬 Integration Tip
Ensure KIE_API_KEY is set in your environment or openclaw.json; the script auto-loads it, so you can invoke without passing env variables. Always download generated tracks immediately as they expire after 14 days.
Scored Sep 13, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.