AvatarSay
Remote MCP server to generate fictional character portraits (8 styles) and lip-synced talking MP4 videos (8 voices) in Claude & Cursor. No subscription.
Hosted MCP Server
npx add-mcp 'https://avatarsay.com/mcp'Installs into Claude Code, Codex, Cursor and more
Documentation
AI Talking Character MCP Server
Point Claude, Cursor or your own agent at one URL to design original D&D NPCs, indie game portraits and anime characters — then turn any portrait into a lip-synced square MP4 video with a built-in voice.
Live endpoint https://avatarsay.com/mcp
No local Python, Docker, or git install. New accounts start with 30 free credits (7 avatar runs = 14 portraits, or 15 NPC voice barks) plus 1 free ≤5 s talking video clip via MCP. One-time packs start at $9.90 and never expire.
Setup in 60 seconds
Connect Claude, Cursor or Windsurf
Sign in once at /dashboard, open the MCP & API keys tab, and create a personal avs_… key. You can also connect without a key first to inspect tools and browse voices and styles.
Cursor / Windsurf
Paste into .cursor/mcp.json or Windsurf MCP config:
{
"mcpServers": {
"avatarsay": {
"url": "https://avatarsay.com/mcp",
"headers": {
"Authorization": "Bearer avs_YOUR_API_KEY"
}
}
}
}
Claude Code (CLI)
Add the remote Streamable HTTP server in one terminal command:
claude mcp add --transport http avatarsay https://avatarsay.com/mcp --header "Authorization: Bearer avs_YOUR_API_KEY"
Claude Desktop (stdio bridge)
Official npm bridge (avatarsay-mcp) for claude_desktop_config.json:
{
"mcpServers": {
"avatarsay": {
"command": "npx",
"args": [
"-y",
"avatarsay-mcp"
],
"env": {
"AVATARSAY_API_KEY": "avs_YOUR_API_KEY"
}
}
}
}
Foundry VTT v12 & v13 Module
In-VTT NPC roller, voice barks & talking portraits
Paste this Manifest URL into Foundry VTT → Add-on Modules → Install Module → Manifest URL:
https://github.com/fourgit/avatarsay-foundry-vtt/releases/latest/download/module.json
SillyTavern Extension
Character Card V2 voices & talking intros
Paste this Git URL into SillyTavern → Extensions → Install extension:
https://github.com/fourgit/avatarsay-sillytavern
Tools, TRPG exports & async design
Ten focused MCP tools, zero blocking timeouts
Roll deterministic D&D / tabletop NPCs with SillyTavern Character Card V2 and Foundry VTT Actor JSON for 0 credits (roll_rpg_npc), import your existing stylized character art (import_character_portrait), synthesize instant (<3 s) MP3 character barks (create_npc_voice_line), or enqueue async 1024 px portraits and 960×960 lip-synced MP4s (generate_avatars + create_talking_video → get_job) without client timeouts.
| Tool name | Auth | Credits | What it does |
|---|---|---|---|
| list_voices_and_styles | Public (no key) | Free | Returns all 8 visual styles, all 8 English TTS voices (with audio sample URLs), credit costs, and pack pricing. |
| roll_rpg_npc | Public (no key) | Free | Rolls a deterministic tabletop RPG / D&D NPC (name, ancestry, role, traits, quirk, plot hook, GM secret, ≤75-char greeting, portrait prompt) plus SillyTavern Card V2 & Foundry VTT Actor JSON. |
| get_credits | Bearer avs_… | Free | Checks your current non-expiring credit balance, image tier (Standard vs HD), free-clip eligibility, and remaining avatar sets, voice barks, or video seconds. |
| list_avatars | Bearer avs_… | Free | Lists recent fictional character avatars in your account with assetId (ast_…) and 24-hour signed image URLs. |
| list_videos | Bearer avs_… | Free | Lists recent rendered 960×960 talking-avatar MP4 videos in your account with 24-hour signed stream and download URLs. |
| generate_avatars | Bearer avs_… | 4 Standard / 6 HD credits | Generates 2 × 1024 px portraits from a text prompt and style. Enqueues asynchronously and returns jobId immediately. |
| import_character_portrait | Bearer avs_… | Free | Imports an existing non-photorealistic fictional character illustration (PNG/JPG/WebP, 256–4096 px, ≤5 MB, confirmFictional: true) from URL or base64 so you can animate VTT tokens or Midjourney art. Real human photos and camera EXIF are blocked. |
| create_npc_voice_line | Bearer avs_… | 2 credits / 100 chars | Synthesizes a fast (<3 s) tabletop NPC voice bark MP3 (1–500 chars) in 8 voices with speed & emotion control and returns a 24-hour signed MP3 URL. |
| create_talking_video | Bearer avs_… | 1st ≤5 s clip free; then 12 credits/s (min 60) | Synthesizes English speech and queues a lip-synced 960×960 MP4 (5–30 s, no watermark). First ≤5 s (≤75 chars) clip on new accounts costs 0 credits. |
| get_job | Bearer avs_… | Free | Polls an image or video job (queued → running → succeeded / failed) and returns 24-hour signed download URLs or automatic refund details. |
Preset styles
8 character art styles
Pass any style ID below to generate_avatars:
- Anime
anime - 3D Cartoon
3d-cartoon - Pixel Art
pixel-art - Realistic
realistic - Professional
professional-headshot - Fantasy
fantasy - Watercolor
watercolor - Cyberpunk
cyberpunk
Built-in English TTS
8 preset character voices
Pass any voice ID below to create_talking_video (no voice cloning):
- Friendly
Friendly_PersonWarm and upbeat, an easy everyday voice. - Warm Woman
Wise_WomanWarm, measured female voice. - Lively Girl
Lively_GirlBright, energetic, younger-sounding female voice. - Calm Woman
Calm_WomanCalm, steady female voice. - Casual Guy
Casual_GuyRelaxed, conversational male voice. - Deep Voice
Deep_Voice_ManLow, resonant male voice. - Patient Man
Patient_ManSlow, unhurried male voice. - Young Hero
Young_KnightYounger-sounding, energetic male voice.
Pay once, use anywhere
No monthly plan required for MCP
Your web studio and MCP keys share the same credit balance. New accounts receive 30 free credits on sign-up — enough to run 7 generate_avatars calls (14 character portraits) or 15 create_npc_voice_line MP3 barks via MCP.
New never-paid accounts also get 1 free talking video clip (up to 5 s / 75 characters, watermark-free) via create_talking_video or /talking-avatar while the limited trial pool lasts. Subsequent or longer talking videos cost 12 credits/s (minimum 5 s = 60 credits).
Starter
$9.90
500 credits · one-time
- ≈ 83 HD avatar pairs
- ≈ 41 s of talking video
- Never expires
Creator
$24.90
1,500 credits · one-time
- ≈ 250 HD avatar pairs
- ≈ 125 s of talking video
- Never expires
Studio
$59.00
4,000 credits · one-time
- ≈ 666 HD avatar pairs
- ≈ 333 s of talking video
- Never expires
Example prompts
What builders run through AvatarSay MCP
D&D & Tabletop RPGs
Session-zero NPC portraits & quest hooks
“Read my campaign notes for Marrowfen Keep, generate fantasy portraits for the three faction leaders with AvatarSay, and render a 6-second talking MP4 of Lord Vane delivering his warning.”
Indie Game Prototyping
Pixel-art & anime dialogue cutscenes
“Generate pixel-art portraits for our shopkeeper NPC, pick the first assetId, and render her opening bark in Lively_Girl voice so we can drop the MP4 into our pitch deck.”
Creator Workflows
Faceless mascot intros from code or docs
“Summarize today’s release changelog into one punchy 10-second spoken line and render a talking video using my existing 3d-cartoon mascot avatar.”
FAQ & safety
Common questions
Questions or directory verification? Email support@avatarsay.com.
Do I need a monthly subscription to use the AvatarSay MCP server?
No. Every new account gets 30 free credits on sign-up (enough for 7 avatar generations or 15 fast NPC MP3 voice lines via MCP) plus 1 free ≤5 s (≤75 chars) talking video clip, and roll_rpg_npc is completely free without even an API key. Paid credit packs are one-time purchases starting at $9.90 for 500 credits and never expire.
Can I upload a real person’s photo or clone a voice through MCP?
No, by design. Real human photographs, camera EXIF captures, face swaps, real public figures, and voice cloning are strictly blocked across both the web app and MCP. For tabletop GMs and indie devs with existing artwork, import_character_portrait accepts non-photorealistic fictional character illustrations (anime, 3D cartoons, pixel art, fantasy paintings, VTT tokens) after EXIF and automated vision safety screening.
Why do generate_avatars and create_talking_video return a jobId instead of waiting?
Lip-synced video rendering takes 3–5 minutes for a short clip (up to 9–14 minutes for 15–30 second clips). Returning jobId immediately prevents Claude, Cursor and HTTP proxies from timing out. Your AI assistant polls get_job until status is succeeded, then gives you a 24-hour signed watermark-free download link. If a render ever fails, credits are refunded automatically.
How are MCP API keys stored and revoked?
Keys start with avs_ and are shown once when created. AvatarSay stores only the SHA-256 hash and a short prefix in the database. You can hold up to 3 active keys and revoke any key immediately in Dashboard → MCP & API keys.