Media tools
Media tools
Endpoints that prepare, inspect, compose and caption media for a generation, beside the image and video routers.
These endpoints work on media you already have or that a job made: trim, inspect, filter, frames, captions, audio, avatars, timelines and references. They use the same API keys, jobs, polling and webhooks as Images and Video.
Endpoints
| Page | What it does |
|---|---|
| Audio detach | Extract the audio track of one Sume-hosted video into a durable wav or mp3. The video is untouched. |
| Create new avatar | Create a reusable avatar with Prompt, Profile, or Image inputs. |
| Avatar video previews | Create first-frame Avatar Video previews, regenerate stills, then generate the final video. |
| Generate avatar video | Generate talking avatar videos from a ready avatar, script or multi-scene inputs, and optional product or scene references. |
| Face swap (Beta) | Beta Avatar Face Swap — apply a ready avatar face onto a public source video. |
| Music 1.0 | Generate music from text (and optional image conditioning) with Sume Music 1.0. |
| Music Router | Music generation through the Music Router — sume/music-auto picks the engine (Lyria 3.5 today); explicit Lyria ids pass through. |
| Reference ingest | Read one reference clip into a timestamped manifest (shots, source-resolution OCR, audio facts, a labeled strip) in one call. Dest first. |
| Remix media | The remix media verbs for one reference clip — probe, word-timed transcript with scores, cut candidates, time- and word-labeled grids, labeled excerpts, notes — each a durable artifact with an id. Dest only. |
| Timeline 1.0 | Assemble one audio spine plus ordered video slots into a long-form MP4. The only public assembly surface. |
| Timeline audio | Concat or split Sume-hosted audio into durable media.sume.com files. Sample-domain join, no re-synthesis. |
| Timeline compose | Put one Sume-hosted still and one Sume-hosted video on screen at the same time. Returns one MP4 shot for Timeline 1.0. |
| Trending videos | Browse or search TikTok trending video metadata for brand, product, creator, or keyword research. |
| Video analyses | Legacy scene-by-scene analysis resource. Dest create is retired (410); production still accepts until #5953 PR-C2. New clip inspection uses video-inspect. |
| Video captions | Burn captions onto an existing public video URL with style, language, and optional script alignment. |
| Video filter | Dim, crop, or apply an allowlisted pixel filtergraph to one Sume-hosted clip. Returns a new MP4. Material preparation, not timeline placement. |
| Video frames | Extract stills from one Sume-hosted clip at times you name. Durable image artifacts at source size. Charged in credits by its compute time. |
| Video inspect | Probe, sample stills from, and optionally transcribe one Sume-hosted clip. Default clip inspection on dest and prod. |
| Video trim | Cut a [start, end) range out of one Sume-hosted clip into a new MP4. Material preparation, not timeline placement. |