Talking photo greeting: 8 seconds on Fabric 720p plus voice-over cost
An 8-second talking-photo greeting on VEED Fabric 1.0 costs $1.50 at 720p or $0.80 at 480p, plus about $0.0114 of TTS for a 240-character line.

A talking-photo greeting that runs 8 seconds on VEED Fabric 1.0 costs $1.50 at 720p and $0.80 at 480p, billed on the audio length. If you generate the spoken line with Sume text-to-speech, a 240-character message adds $0.0114. The whole greeting is about $1.5114 at 720p.
The price build-up
Fabric 1.0 takes a still image and an audio file and returns a video where the image speaks the audio. It is priced per second of audio, not per second of video, and the audio file must be Sume-hosted and under 10 MB. The maximum audio length is 300 seconds.
| Item | Quantity | Rate | Cost |
|---|---|---|---|
| Fabric 720p | 8 s audio | $0.1875/s | $1.50 |
| Fabric 480p | 8 s audio | $0.10/s | $0.80 |
| TTS line | 240 characters | $0.0475 per 1,000 | $0.0114 |
| Total at 720p | $1.5114 | ||
| Total at 480p | $0.8114 |
How the pieces fit
Write the line first, since the speech time sets the price. Eight seconds of speech is roughly 20 to 24 words. Generate the audio with text-to-speech, take its duration, and send it to Fabric with the image. The request body uses audio_url, duration_seconds, and either image_url or an avatar_handle if you already created one.
Using a handle instead of a loose image means you pay the $0.95 creation fee once, then reuse the face for later greetings. For a one-off card, a plain image URL avoids that fee.
- Keep the audio under 10 MB and host it on Sume first.
- Set
duration_secondsto the true length of the audio file, since billing follows it. - Use 480p for chat-size cards and 720p when the card will be shown full screen.
When to choose another route
Sume Avatar 1.0 talking video starts at $0.184 per second, which would be $1.472 for 8 seconds, but it speaks a script through an avatar. Fabric is the route when you already have the exact audio, for example a recorded voice message. MiniMax H3 Max Lip Sync starts at $0.0625 per second at 480p but needs 5 to 14.8 seconds of audio. See the model docs and the catalog.
Limits to check
A 300-second ceiling is far above any greeting, so the limit that matters is audio size. Compressed audio at 8 seconds is well under 10 MB. A failed job is not charged, because the reserved amount is refunded when a job fails or is canceled.
Sources
Related posts
More in Media tools
- Korean captions API error: caption_hangul_text_latin_style (400)
Sume refuses Korean text on the slam, punch and tiktok-green caption styles with a 400. Use black-outline, korean-ad or another Hangul style; $0.20 a job.
- caption_no_speech: burn authored cues onto a silent clip, no ASR
A silent clip makes speech-to-captions fail with caption_no_speech. Send cues (text, start, end) and Sume burns your text at those times without speech-to-text.
- Caption a silent clip with 3 timed cues: $0.20, no speech needed
A silent clip fails Sume video captions with caption_no_speech. Send cues with text, start and end to burn overlay text instead. One job, $0.20 up to 60 s.
- Check pause-cut seams with video frames: 24 stills cover 12 seams
Video frames returns up to 24 stills per call. Two stills per seam covers 12 seams per call, so a 14-cut Reel needs 2 calls to see every join.
Written by Sume