VEED Fabric Emotions audio tags vs Sume Fabric audio_url
VEED's Fabric Emotions adds inline tags like [excited] in the script. On Sume, Fabric takes a finished audio_url; emotion lives in the TTS step.
On Sume, Fabric takes a finished audio file, not a script with tags. VEED's Fabric Emotions page, read 2026-10-01, describes inline [tag] audio tags for emotions, reactions, tone and sound effects such as applause, powered by ElevenLabs V3 (Alpha). To get emotion on Sume, set it when you make the audio.
What does Sume's Fabric accept?
POST /v1/veed/fabric-1.0 takes audio_url on the Sume host (max 10 MB), duration_seconds 1 to 300, resolution 480p or 720p, speed_tier standard or fast, and exactly one of image_url or avatar_id/avatar_handle.
| Item | VEED Fabric Emotions | Sume Fabric |
|---|---|---|
| Emotion input | Inline [tag] audio tags in the script | emotion string in the TTS generation_config (up to 64 characters) |
| Audio input | Script with tags | audio_url on the Sume host (max 10 MB) |
| Duration | Not covered here | duration_seconds 1 to 300 |
| Resolution | Not covered here | 480p or 720p |
Where does emotion come from?
From the TTS call before it. Sume's TTS generation_config has an emotion string up to 64 characters, plus speed and volume. Generate the voice, import it, then pass its audio_url to Fabric.
What do I lose?
Inline tags mid-sentence, and sound effects spoken inline. For effects, make them with the sound-effects model and mix them in with Timeline.
Sources
Related posts
More in Sume Avatar 1.0
- Add a pause to an AI avatar video with a silence beat
To make a Sume avatar stop talking for a few seconds, use a silence scene in video_inputs: duration required, no script allowed. Example, limits and cost.
- AI face swap video cost: the $2.76 to $8.25 ceiling per clip
Sume's Beta avatar face swap reserves a 15-second maximum: $2.76 on standard, $3.68 on plus, $8.25 on max. Constraints and when to use talking video instead.
- avatar-1.0/image-to-video is deprecated: switch to veed/fabric-1.0
Sume's avatar-1.0 image-to-video routes are deprecated aliases of VEED Fabric 1.0. Same body, new URL: audio_url, duration_seconds and one image source.
- Avatar 1.0 talking video: 4 to 60 seconds, cost by quality tier
Work out what a 4, 15, 30 or 60 second Avatar 1.0 talking video costs at standard, plus and max quality, using the per-second rates in the Sume catalog.
Written by Sume