# AvatarSay — Fictional Character & Talking Video MCP

> AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media. Generate fictional character portraits and lip-synced talking videos from text over MCP. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://avatarsay.com/mcp
- **Repository:** https://github.com/fourgit/avatarsay-mcp
- **MCP Registry name:** io.github.fourgit/avatarsay-mcp
- **Categories:** design and media, games and play
- **Listing updated:** 2026-11-15

## About

AvatarSay is built around original, fictional characters made from a text prompt: RPG NPCs, anime original characters and game portraits. The server says it does not accept photo uploads, face swaps, real public figures or voice cloning. A portrait job returns two 1024 px images in one of 8 styles, and a talking video turns a portrait into a 960 by 960 MP4 of 5 to 30 seconds with one of 8 built-in English voices and no watermark.

Because video renders take about 3 to 5 minutes (longer for long clips), generate_avatars and create_talking_video return a job id immediately, and the assistant polls get_job for signed download links valid for 24 hours. Failed jobs are refunded automatically.

Tool discovery is open, but account tools need a personal avs_ bearer key created in the dashboard. Credits are bought as one-time packs; there is no subscription.

## Features

- **Eight art styles:** Anime, 3D cartoon, pixel art, realistic, headshot, fantasy, watercolor and cyberpunk.
- **Talking video:** Lip-synced 960x960 MP4, 5 to 30 seconds, no watermark.
- **Eight English voices:** Preset voices; voice cloning is not supported.
- **Async jobs:** Long renders return a job id to poll instead of blocking.
- **Auto refunds:** Failed jobs return their credits.
- **Remote or bridge:** Connect over streamable HTTP or via a local stdio bridge.

## Good for

- Create portraits for D&D non-player characters
- Make anime original characters for a story
- Turn a character into a short talking clip
- Generate indie game character art
- Preview voices and styles before spending credits

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http avatarsay-mcp https://avatarsay.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://avatarsay.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "avatarsay-mcp": {
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "avatarsay-mcp": {
      "type": "http",
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "avatarsay-mcp": {
      "serverUrl": "https://avatarsay.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "avatarsay-mcp": {
      "type": "http",
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

## Tools

- `list_voices_and_styles`: Return all 8 AvatarSay visual styles, all 8 built-in English TTS voices (with audio sample URLs), per-action credit costs (including first free 5s talking clip and 2-credit NPC voice lines), and one-time credit pack pricing. Public read-only tool — does not require an API key.
- `roll_rpg_npc`: Deterministically roll a complete tabletop RPG / D&D NPC (name, ancestry, role, traits, quirk, plot hook, GM secret, portrait prompt, matched voice sample MP3, and a <=75-char greeting tuned for the free 5s talking video clip), plus ready-to-import SillyTavern Character Card V2 JSON and Foundry VTT NPC Actor JSON. Public zero-cost tool — requires NO API key and charges 0 credits.
- `get_credits`: Return the authenticated AvatarSay account email, current non-expiring credit balance, image quality tier (standard vs hd), whether the 0-credit first talking video clip is still available, and how many avatar generations, NPC voice lines, or video seconds the balance covers. Requires Authorization: Bearer avs_...
- `list_avatars`: List recent fictional character avatars (both AI-generated portraits and imported stylized character illustrations) in this AvatarSay account, including assetId (ast_...) and 24-hour signed download URLs, ready to animate with create_talking_video. Requires Authorization: Bearer avs_...
- `import_character_portrait`: Import an existing non-photorealistic fictional character illustration (anime, 2D/3D cartoon, pixel art, fantasy digital painting, VTT token art; PNG/JPG/WebP, 256–4096 px, max 5 MB) from an https:// URL or base64 data URI for 0 credits, returning an assetId (ast_...) ready for create_talking_video. Camera photographs and photorealistic human likenesses are strictly blocked by EXIF and automated v
- `list_videos`: List recent watermark-free talking avatar MP4 videos (960×960) already rendered in this AvatarSay account, including assetId (ast_v_...), spoken script, and 24-hour signed stream & download URLs. Requires Authorization: Bearer avs_...
- `generate_avatars`: Generate 2 square (1024×1024) fictional character portraits from a text description in one of 8 art styles. Costs 4 credits (Standard) or 6 credits (HD for accounts that have purchased a pack). Enqueues asynchronously and returns jobId immediately — call get_job after ~5–10 seconds to get the 2 assetIds and signed image URLs. Requires Authorization: Bearer avs_...
- `create_npc_voice_line`: Synthesize an instant (<3s) English character voice bark or tabletop NPC dialogue MP3 (1–500 chars) in one of 8 preset voices with optional speed and emotion control. Costs 2 credits per 100 characters (minimum 2 credits — a new 30-credit account can generate 15 tabletop MP3 barks free). Returns a 24-hour signed MP3 download URL immediately. Requires Authorization: Bearer avs_...
- `create_talking_video`: Animate an AvatarSay character avatar (ast_...) with lip-synced English speech in one of 8 preset voices. New accounts get their first short talking clip (<=5s / <=75 chars) for 0 credits! Subsequent or longer clips cost 12 account credits per second of speech (minimum 5s = 60 credits, maximum 30s). Enqueues asynchronously and returns jobId immediately — never blocks for the 3–5 minute render. Pol
- `get_job`: Check the status (queued, running, succeeded, failed) of an image or talking-video job (job_...) and return 24-hour signed download URLs once succeeded, or refund details if failed. Requires Authorization: Bearer avs_...

## FAQ

### Is there a subscription?

No. Credits come in one-time packs from $9.90 and do not expire.

### Is anything free?

New accounts get 30 free credits, enough for 7 avatar generations (14 portraits).

### Can it use a real person's photo?

No. It generates fictional characters from text only.

### How long do videos take?

Roughly 3 to 5 minutes, and 9 to 14 minutes for 15 to 30 second clips.

### Is AvatarSay — Fictional Character & Talking Video MCP free?

AvatarSay — Fictional Character & Talking Video MCP has a free plan, with paid plans for more usage or features.

### How do I add AvatarSay — Fictional Character & Talking Video MCP to Claude Code?

Run this command in your terminal: claude mcp add --transport http avatarsay-mcp https://avatarsay.com/mcp

### What are the best alternatives to AvatarSay — Fictional Character & Talking Video MCP?

The closest alternatives to AvatarSay — Fictional Character & Talking Video MCP are HyperFrames by HeyGen, ffmpeg-skill, ChartAnt, VfxSmith and CalderFlow.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [Hourlore](https://ai-powered.com/mcp/hourlore): Hourlore is a freemium MCP server for design and media.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [PugSoda](https://ai-powered.com/mcp/pugsoda): PugSoda is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp
