trackyardSearch and download licensed music from Trackyard's AI-powered catalog. Use for finding background music for videos, social content, podcasts, or any project...
Install via ClawdBot CLI:
clawdbot install benny-conn/trackyardTrackyard gives you instant access to tens of thousands of curated tracks — every song 100% legally cleared for social media, YouTube, podcasts, and online content (non-film/TV). Three things make it stand out:
Requires TRACKYARD_API_KEY environment variable. Users get an API key at trackyard.com.
export TRACKYARD_API_KEY="trackyard_live_..."Or add to OpenClaw config: env.vars.TRACKYARD_API_KEY
scripts/trackyard.sh search "upbeat electronic for tech startup video"With filters:
scripts/trackyard.sh search "chill background music" --limit 5 --no-vocals --energy mediumFull track:
scripts/trackyard.sh download TRACK_IDTrimmed to 22 seconds:
scripts/trackyard.sh download TRACK_ID --duration 22With hit-point alignment (drop lands at 12s mark):
scripts/trackyard.sh download TRACK_ID --duration 22 --hit-point 12scripts/trackyard.sh me| Filter | Values |
|--------|--------|
| --genres | electronicDance, pop, rock, hiphop, ambient, classical, jazz, etc. |
| --moods | happy, energetic, sad, calm, dramatic, mysterious, romantic |
| --energy | low, medium, high |
| --min-bpm / --max-bpm | 60-200 |
| --no-vocals | Instrumental only |
| --instruments | synthesizer, guitar, piano, drums, strings, etc. |
When downloading with --duration:
--hit-point N places the peak/drop at N seconds into the clip.mp3 to current directory (filename from track title)Generated Mar 1, 2026
Automates music selection for platforms like TikTok, Instagram Reels, and YouTube Shorts by searching with natural language queries and trimming tracks to exact durations (e.g., 15s, 30s). Ideal for content farms producing videos at scale, ensuring brand-safe, royalty-free music that matches video themes.
Pairs AI-generated video content with AI-selected music by feeding video descriptions into the search function and clipping results to match video lengths exactly. Enhances automated video pipelines for marketing, entertainment, or educational content.
Finds professional, neutral background music for corporate videos, training materials, and product demos, using filters like low energy and no vocals to avoid distraction. Supports branding consistency and viewer engagement in business communications.
Searches for instrumental, low-energy tracks to complement voiceovers in podcasts or YouTube videos, with smart trimming to fit episode lengths. Ensures music enhances content without competing with spoken audio.
Selects brand-safe tracks for social media ads or product trailers, using hit-point alignment to sync musical peaks with key visual moments. Optimizes emotional impact and viewer retention in marketing campaigns.
Offers tiered subscription plans for API usage, charging based on credits for searches and downloads. Targets businesses needing scalable music licensing, with revenue from monthly or annual fees and overage charges.
Provides a free tier with limited credits to attract individual creators, then sells credit packs for additional searches and downloads. Appeals to small teams and hobbyists, generating revenue from one-time purchases.
Sells custom enterprise licenses to large media companies or tech firms for integration into video editing software or content management systems. Includes premium support and bulk discounts, driving high-value contracts.
💬 Integration Tip
Set the TRACKYARD_API_KEY environment variable and ensure curl and jq are installed; use natural language search queries for best results and leverage hit-point alignment to sync music with video moments.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
End-to-end encrypted agent-to-agent private messaging via Moltbook dead drops. Use when agents need to communicate privately, exchange secrets, or coordinate without human visibility.
Text-to-speech via OpenAI Audio Speech API.