Donor thank you video: one render, each donor's name

A donor thank you video is a short message from someone at your organization that thanks the donor by name and says what the gift makes possible. To send one to every donor without recording each clip, either render one thank-you and burn each donor's name on screen with a caption job per donor, or render a separate talking video per donor that says the name aloud. With Sume, the first costs one render plus $0.20 per name; the second costs a full render per donor.

The Sume facts below come from the Generate avatar video, Create new avatar and Video captions docs, the caption schema in the Sume API reference, and Sume's Terms of Service, read on 2026-09-29. Prices are read from the code behind API pricing; points marked as current behavior are read from Sume's code.

What should a donor thank you video say?

Keep it to one message: thank you, what this gift does, and one concrete detail from your program, from a person donors know, such as your director. Don't ask for another gift in the same video. The same script works as a volunteer thank-you video with the verb changed. Fundraising video ideas covers the campaign videos that come before it.

How do I add each donor's name without re-recording?

Render the thank-you once with POST /v1/avatar-1.0/talking-video, opening on a line such as “Thank you for your gift,” which is where the name will appear. Then send that video to POST /v1/video-captions once per donor with an authored cues entry: the job skips speech-to-text and burns exactly that text at the times you set. Each caption job is $0.20 for videos up to 60 seconds. In current code the job refuses videos over 60 seconds or without an audio stream; a talking video has speech, so it qualifies. The default style for Latin text, slam, uppercases text in current code, so try one name first.

curl -X POST https://api.sume.com/v1/video-captions \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: thanks-donor-0001" \
  -d '{
    "video_url": "https://media.sume.com/artifacts/artf_demo/thank-you.mp4",
    "cues": [
      { "text": "Thank you, Maria", "start": 0, "end": 3.5 }
    ]
  }'

Can the video say each donor's name out loud?

Yes, by rendering one talking video per donor with the name in the script. Sume accepts a script when it estimates the video at 4 to 60 seconds. In current code the avatar speaks English only, and the avatar-video docs describe no pronunciation control, so watch the clips for names that come out wrong. For a long list, run one job per row; personalized video at scale covers batching and matching each video back to its person.

How much does each path cost?

Both paths start from the same presenter; creating an avatar is $0.95 per avatar. The table uses a 30-second video at the default quality, $0.245 per second, so one render is about $7.35.

What about consent and donor data?

Sume's terms say you represent that you have permission to use any person's likeness or voice, so get the director's agreement before you create an avatar from their photo. The terms also ask you not to submit private information you don't have permission to use. A first name is enough for the caption or script; keep gift amounts, addresses and notes out of every request.