Reference audio for AI video: which models accept a voice clip
Seedance 2.5, Wan 3.0 and MiniMax H3 take reference audio on Sume; Kling 3, Gemini Omni Flash and the swap rows do not. Limits and the one-reference rule.
Reference audio works on Seedance 2.5 and the Seedance 2.0 rows, Wan 3.0, MiniMax H3 and MiniMax H3 Max. Kling 3 has no reference inputs at all, Gemini Omni Flash 1.1 takes image and video references but not audio, and Genjutsu and H3 Max Recast refuse audio references. Where it is accepted, audio cannot be the only reference: send at least one reference image or video with it.
Limits by model
Counts below are the catalog constraints for the rows that publish them. For Seedance, see the linked post on how reference types mix, since the cap there is a total rather than a per-type number.
| Model id | Reference audio | Limit |
|---|---|---|
| wan-3.0 | yes | up to 5 clips, 15 s total |
| minimax-h3, minimax-h3-max | yes | up to 3 clips, 2 to 15 s each, 15 s combined; images, videos and audios total 12 |
| seedance-2.5 | yes | needs an image or video reference alongside |
| kling-3 | no | reference_*_urls rejected |
| gemini-omni-flash-1.1 | no | no reference_audio_urls |
| genjutsu, h3-max-recast | no | audio references rejected |
Using it
Reference audio is for matching a voice, a beat or a mood, not for pasting a finished soundtrack under the clip. For a finished track, generate the video and mix the music on a timeline afterwards.
Audio URLs must be public HTTPS. MiniMax and Wan enforce duration limits on each clip, so trim an audio file before submitting rather than relying on the model to cut it.
A quick check before you submit
If your request has only reference_audio_urls, it will be refused. Add a first-frame image or a reference image, then retry.
Sources
Related posts
More in Models
- Reference videos in AI video on Sume: Wan, H3, H3 Max and Omni limits
How many reference images, videos and audio files each Sume video model accepts: Wan 10/5/5, H3 9/3/3, Omni 10/3 with 3-second clips, Kling none.
- Omni Flash vs H3 Max for reference-to-video: limits side by side
Gemini Omni Flash 1.1 takes 10 images and 3 short videos; MiniMax H3 Max adds audio refs, 12 files total. Limits, tags and a sample request on Sume.
- Runway Veo negativePrompt: 1,000 characters, and Sume's options
Runway's API takes an optional negativePrompt of up to 1,000 characters on three Veo models. Sume's video request lists no such field, so use positive wording.
- Seedance 2.5 'extend twice': what Sume's 30-second request does
ByteDance says Seedance 2.5 makes up to 30 seconds with two extensions. Sume's seedance-2.5 id takes 4-30 seconds per request and has no extend field.
Written by Sume