Which Synthesia plan includes API access? Pro is limited

Synthesia lists no API on Basic or Starter, a limited API with 360 minutes a year on Pro, and full access on Enterprise. What a Sume API key gives you instead.

4 min readSume
All posts

Per Synthesia's pricing page, read on 2026-10-01, the Basic ($0) and Starter ($29 a month) plans have no API access, Pro ($89 a month) has a limited API with 360 minutes a year included, and full API access is an Enterprise feature. If you are a developer who wants to render avatar videos from code today, that matters more than the avatar count. On Sume, an API key is enough to call the Avatar 1.0 routes, and the cost is per second of video rather than a plan tier.

This is a plan-gating comparison, not a quality ranking. Synthesia's plans bundle an editor, avatars, dubbing and collaboration; the API is one line in that bundle.

Synthesia plans, as listed

The rows below are only the parts that affect an API decision.

From Synthesia pricing, read 2026-10-01, monthly billing. Annual billing lowers the monthly price on Starter and Pro; the page also lists credits and avatar counts.
PlanMonthly priceCredits per monthAPI
Basic$0500 (and a 10 minute video allowance)No API access; watermark
Starter$291,250 (about 12 minutes of video)No API access
Pro$896,000 (about 60 minutes)Limited; 360 minutes a year included
EnterpriseCustomUnlimited video minutesFull API access

What the Sume side looks like

Sume's Avatar 1.0 flow is two calls. Create a reusable avatar with POST /v1/avatar-1.0/generate from a prompt, a profile or a reference image, and poll the job. Then call POST /v1/avatar-1.0/talking-video with the returned avatar_handle and either a script or an ordered video_inputs plan. Scripts are accepted when Sume estimates 4 to 60 seconds of speech.

Billing is a rate card. At the time of writing, creating an avatar is a flat $0.95, and a talking video is $0.184 per second on standard, $0.245 on plus and $0.55 on max. So a 30-second plus video is $7.35. Read the live numbers from GET /v1/catalog before you budget.

curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: weekly-update-w40" \
  -d '{
    "avatar_handle": "studio_presenter",
    "script": "This week we shipped three fixes and one new report.",
    "mode": "webhook",
    "webhook_url": "https://example.com/hooks/sume"
  }'

Where Synthesia is still the better answer

  • You need a person to edit scenes, brand kits and templates in a browser. The Sume API has no scene editor.
  • You need real-time conversation. Synthesia lists interactive Sessions as live; Sume renders finished clips only.
  • You need videos longer than a minute in one render. A Sume job is capped at 60 seconds, and the output is 720p.
  • You want dubbing in 140 plus languages from one tool. Sume's documentation covers avatar, captions, audio and timeline pieces, not a one-click dubbing product.

Limits

Plan names, credits and API terms can change at any time, and the Pro "limited API" is not defined beyond the minutes on the page, so ask Synthesia what is excluded before you build on it.

Sources

Related posts

More in Comparisons

All Comparisons posts

Written by Sume