Turn two portrait photos into a Hotel Lobby AI duo video.
AvatarSay
AvatarSay — Type one sentence to generate a fictional AI character that talks — pay-once, no subscription.
About AvatarSay
AvatarSay turns a written description into two 1024px original fictional characters across 8 visual styles (anime, 3D cartoon, pixel art, fantasy, cyberpunk, watercolor, realistic, professional), then animates one into a lip-synced talking MP4 up to 30 seconds in 8 English voices.
Every face is generated purely from text: there are no photo uploads, no face swaps, and no voice cloning, so nobody's real likeness is used. Developers and creators can also generate avatars and talking clips directly inside Claude Desktop and Cursor via the remote MCP server (https://avatarsay.com/mcp). New accounts get 30 free credits and a free 5-second talking clip; one-time credit packs start at $9.90 and never expire.
- Who it is for
- Faceless Shorts & TikTok creators, tabletop RPG game masters, indie game devs, and AI agent builders.
- Problem it solves
- Most AI talking avatar tools require $24–$29/month subscriptions whose unused credits expire every 30 days, and center around uploading real human photos.
- The solution
- Describe an original fictional character in one sentence and export a lip-synced MP4 on one page or via MCP—paying once from $9.90 with credits that never expire.
- What makes it unique
- 100% text-generated fictional faces (zero photo uploads or face swaps), $9.90 non-expiring pay-once credit packs instead of monthly plans, plus a live remote MCP server (/mcp).
Features
Text-only fictional characters
Generate two 1024px original avatars from one text sentence with zero photo uploads.
8 distinct visual styles
Anime, 3D cartoon, pixel art, fantasy, cyberpunk, watercolor, realistic, and professional.
Lip-synced MP4 up to 30s
Turn any generated character into a talking MP4 clip in 8 built-in English voices.
Remote MCP server (/mcp)
Generate character portraits and talking videos directly inside Claude Desktop and Cursor.
Zero likeness or voice cloning
No photo uploads, face swaps, or voice cloning—safe for fictional storytelling and NPCs.
Pay-once credits never expire
One-time packs start at $9.90 with no recurring subscription or monthly reset.
Details
- Platforms
- Web
- Pricing
- Freemium
- Usage-based
- Built for
Faceless Shorts & TikTok creators, tabletop RPG game masters, indie game devs, and AI agent builders.
- Building since
2026
Technology
AvatarSay product screenshot
1 / 1Website performance
Recorded mobile lab measurements and finalized weekly standings from IndieTools Speed.
AvatarSay website speed overview
99
Performance scoreGood
In IndieTools' mobile lab test on November 15, 2026, the AvatarSay website scored 99 out of 100 (good). All 5 lab metrics were rated good.
Measured (UTC)
- LCPLargest Contentful Paint
- 1.06 s
- Good
- TBTTotal Blocking Time
- 18 ms
- Good
- CLSCumulative Layout Shift
- 0.012
- Good
- FCPFirst Contentful Paint
- 1.06 s
- Good
Not ranked in a finalized week yet.
AvatarSay lab metrics
| Metric | Result | Status | Trend |
|---|---|---|---|
| Mobile lab testMid-range phone on a throttled 4G connection, two runs averaged. Changes compare with the run on Nov 15. | |||
| Performance score GoodUp 1 points | 99 / 100 | GoodUp 1 points | |
| First Contentful Paint GoodAbout the same | 1.06 s | GoodAbout the same | |
| Largest Contentful Paint GoodAbout the same | 1.06 s | GoodAbout the same | |
| Speed Index Good1.61 s faster | 2.40 s | Good1.61 s faster | |
| Total Blocking Time Good18 ms slower | 18 ms | Good18 ms slower | |
| Cumulative Layout Shift Good0.012 more shift | 0.012 | Good0.012 more shift | |
| Unthrottled observationsTimed on the test machine's own fast connection, so they read lower than the lab metrics above. | |||
| Page load 77 ms faster | 505 ms | 77 ms faster | |
| Server response About the same | 3 ms | About the same | |
AvatarSay performance history
2 comparable mobile lab runs since November 15, 2026. Choose a metric and a range, then move along the line to read each run.
AvatarSay Speed ranking
Not ranked yet. Ranks appear once a week with this product is finalized.
Stored lab observations from controlled test runs, not real-user Core Web Vitals or a guarantee of search rankings. Weekly standings remain attached to their finalized edition.Method psi-mobile-two-sample-mean-v1, 2 samples per reading. Lab results can vary between runs.
Domain Rating
Domain Rating by Ahrefs- DR4 (primary model)
- 0
First DR4 reading
- DR3
- 1
First DR3 reading
Model difference−1. DR4 is 1 point lower than DR3.
Measured · avatarsay.com
What do DR4, DR3 and the model difference mean?
- DR4:
- Ahrefs' newer model. It gives more weight to links from sites with organic search traffic and rates a subdomain on its own links.
- DR3:
- The previous model, shown in the Ahrefs app until 1 December 2026.
- Model difference:
- DR4 minus DR3 for the same domain. The models calculate differently, so this is not growth or a drop; the “since” lines compare each model with itself.
Related products
Others in the same categories.
Direktori Website & Layanan Digital
Free AI Speaking Coach for English Speaking Practice
AI UGC videos from your product link
AI rap video generator from photos — duo mode by default
Free AI Business Document Generator
