Skip to main content
Find background music by describing the vibe you want (“upbeat lofi hip-hop”, “tense cinematic riser”, “subtle ambient corporate”) and get back ranked tracks, each with a pre-signed download URL. Search is semantic, not keyword-based, so plain-language descriptions work best.

Search the Catalog

Send a GET request to /v3/audio/sounds with a natural-language query:
Each result in data has an id, name, description, audio_url (a pre-signed WAV link), duration in seconds, and a score (0–1 semantic similarity), returned highest-first with type music. The reference has the full schema. Parameters worth tuning:
  • limit: 1–50 results per page (default 10).
  • min_score: minimum similarity, default 0.7. Tracks scoring below it are omitted, so raise it for tighter matches and lower it to widen the net.
  • type: music (the default) searches the background-music catalog; sound_effects searches sound effects.
  • token: when has_more is true, pass the returned next_token as token to fetch the next page.
Each audio_url is a pre-signed link with a limited lifetime. Download the file (or hand the URL to a downstream step) soon after searching rather than caching it for later.
Searching from an AI agent instead of code? The same catalog is available through the HeyGen MCP via the search_audio_sounds tool.