Use audio from a TikTok or Instagram link in your video
Sume imports a public TikTok or Instagram URL, detaches its audio as wav or mp3, then lays it under a Timeline render. YouTube links are rejected.

Paste a public TikTok or Instagram URL into POST /v1/media-imports, detach the audio with POST /v1/audio-detach, then use the resulting file as soundtrack or audio.url in a Timeline 1.0 render. Any other host, YouTube included, is rejected with unsupported_platform.
OpusClip's September 30 changelog entry describes the same idea inside an editor: drop in a file or paste a link and the audio is pulled out. This post is the API version of that chain, from the Sume docs and OpenAPI file read 2026-10-01.
Which links does the import accept?
The OpenAPI description for submitMediaImportJob says it imports a public TikTok or Instagram video URL into Sume-owned storage, and that YouTube and other hosts are rejected with unsupported_platform. The request body requires only url. The result is a file on media.sume.com, which is the only kind of source the other audio tools read.
If your link is to a private account or a non-video page, treat it as unsupported; the schema describes public video or reel URLs. For the Instagram side of this, see Instagram reel download API.
How do I turn the imported video into an audio file?
Send the imported media.sume.com URL as video_url to audio detach. The format field is wav (default, pcm_s16le, sample-exact) or mp3 (128 kbps), and an optional range takes { start, end? } in seconds so you keep only the part you want. Detach needs an Idempotency-Key, and a source with no audio track fails with detach_source_has_no_audio. The full walk-through is in extract audio from a video URL.
How do I use that audio under my video?
Pass the detached audio_url to Timeline 1.0. As a soundtrack it is an optional bed with url, gain_db, loop, fade_out_seconds (up to 10) and duck_db. As audio.url it becomes the single spine that sets the render's audio.
| Step | Endpoint | Failure to expect |
|---|---|---|
| Import the link | POST /v1/media-imports | unsupported_platform for YouTube and other hosts |
| Detach the audio | POST /v1/audio-detach | detach_source_has_no_audio, audio_detach_range_empty |
| Render with the bed | POST /v1/timeline-1.0/render | unsupported_media_source for an off-host URL |
What should I check before using someone else's audio?
Importing a public URL does not tell you whether you may reuse the sound in your own video. Rights to the track are your call; check the source's terms before publishing. For a bed you control, see mix voice with background music.
Sources
Related posts
More in Use cases
- Wan-Dancer 14B music-to-dance vs an audio reference on Wan 3.0
Wan-Dancer-14B (Apache 2.0, 2026-07-13) turns music into dance video locally. On Sume, Wan 3.0 accepts an audio reference on clips of 2-30 seconds.
- Apple Watch Ultra 4 screenshot size: 422x514 from Sume
Apple Watch Ultra 4 screenshots are 422 x 514 pixels. Sume's image API cannot output that size, but a Timeline still plus a PNG frame can.
- Wix Video minimum size 480x470: crop and scale with video filter
Wix Video accepts 480x470 to 1920x1080. Sume video-filter crops by fractions and runs scale or pad in a filtergraph, with a free check before the encode.
- Wix video poster 1944x2880: stills from a clip with video frames
Wix lists a video poster at 1944 x 2880 px. Sume video-frames makes JPG or PNG stills from a clip, but max_edge stops at 2160, so it cannot upscale to 2880.
Written by Sume