Reels audio types: original, licensed, voiceover, and an AI voice file
Instagram's Reels page names original audio, licensed music and Voiceover. Where a Sume-made voice file fits, and what the page does not say.

Instagram's Reels page lists three kinds of audio: original audio (audio you created in the app or in an uploaded video), licensed music from its library, and Voiceover on clips (read 2026-10-03). A voiceover file made with Sume and mixed into your video before upload is part of the video you upload, so it is original audio under that definition. Instagram's page does not mention AI-generated speech, so any labeling rules live elsewhere.
The three types
Here is how each type maps to a Sume workflow, based only on what Instagram's page says.
| Instagram audio type | What the page says | Sume side |
|---|---|---|
| Original audio | Audio you created in-app or in an uploaded video | A mixed video with a Sume voice track is uploaded as the video |
| Licensed music | Library music, movies, TV and sound effects | Not something Sume provides |
| Voiceover | Added to clips in Reels | Record in-app, or bring a finished voice track in your video |
Making the voice file
Create it with tts_create: transcript up to 20,000 characters, a voice.id, and a language code. Pick mp3 or wav output. See MCP tools and gates. Mix it into the video in Timeline, then export the final file to upload.
The Instagram page also says downloading a reel will not save music added from its library. That concerns library music only, not audio baked into your own file.
Sources
Related posts
More in Use cases
- Reels templates need music and 3 clips: build the match in Timeline
Instagram says Reels templates need music and at least 3 clips. Build the same shape outside the app: a 3-slot Sume Timeline with a soundtrack.
- Instagram's three Reel length tiers: cut one talk into 15, 60, 180 s
Instagram's Reels guide names three length tiers up to 3 minutes. Cut one source clip into all three with Sume video trim and compare the versions.
- 3-minute Reels on Timeline: 61 seconds bills as two minutes
Sume Timeline charges $0.10 per started output minute. A 60-second cut is $0.10, 61 seconds is $0.20, and 180 seconds is $0.30. Plan the trim before you render.
- Instagram Replace Audio on a published post, or re-render with Sume
Instagram added audio replacement on published feed posts. Sume can render a new soundtrack but cannot feed it into that flow. Which route keeps what.
Written by Sume