Tavus lists 1080p conversational video; Sume avatar clips are 720p
Tavus's pricing page lists 1080p and 24 kHz audio on all plans; Griffin-Lite renders 720p. Sume avatar videos are 720p today. What that means for your delivery.
Tavus's pricing page lists 1080p resolution and 24 kHz audio fidelity as part of its conversational video interface on every plan, while its Griffin page says the research-preview Griffin-Lite generates 720p video in 320 ms chunks and is not available to customers yet. Sume's avatar talking video has a resolution of 720p today. So the number to compare is the shipped one: 1080p for Tavus's conversation product, 720p for Sume's rendered clips.
Sources: Tavus pricing and Griffin, read 2026-10-04; Sume Generate avatar video.
What each page states
Be careful to keep the products apart: the pricing page describes the shipping conversational interface, and the Griffin page describes a model that is a preview for selected testers.
| Product | Stated output | Availability |
|---|---|---|
| Tavus conversational video interface | 1080p, 24 kHz audio | On every listed plan |
| Tavus Griffin-Lite | 720p in 320 ms chunks | Research preview, selected trusted testers |
| Sume avatar talking video | 720p (current resolution value) | API, all quality tiers |
Does 720p matter for your placement
For a 9:16 phone feed, 720p wide by 1280 tall is the common floor and looks fine on a handset. For a 16:9 web hero shown full screen on a large monitor, the gap shows. Decide from where the clip plays, not from the spec sheet.
- Phone feeds and chat: 720p is usually enough.
- Full-screen desktop: check on the real display.
- Paid placements: read the platform's minimums before you render.
What Sume offers instead of more pixels
Quality tiers (standard, plus, max) change the render path, not the output size. Previews let you check framing before the render. If you need a bigger file, test an upscale as a separate step and judge whether it adds real detail or only size.
Bottom line
Pick on use: live conversation at 1080p points to Tavus; script-driven presenter clips at 720p fit Sume. Keep Griffin-Lite out of any plan until it is available to customers.
Sources
Related posts
More in Comparisons
- Is there a Tavus Griffin-Lite API? Not yet, and what to use
Tavus says Griffin is not available to customers, only to select trusted testers. Sume's avatar video API ships today with 4-60 s clips and five ratios.
- Tavus Starter: 3 concurrent streams vs Sume bulk concurrency 1 to 16
Tavus Starter caps live conversations at 3 concurrent streams. Sume bulk runs queue up to 100 renders and keep 1 to 16 in flight. Different jobs.
- TTS language counts in October 2026: Voxtral 9, MAI 23, ElevenLabs 90+
How many languages each TTS vendor states: Mistral Voxtral, Microsoft MAI-Voice-2.1, OpenAI and ElevenLabs, from vendor pages, plus Sume's language field.
- TTS latency numbers side by side: Eleven v4 Turbo, Voxtral, MAI Flash
Three vendors, three latency figures, three different things measured. A table of what each page says, and why a Sume TTS job is a different question.
Written by Sume