Sync MCP Server

What it does

Sync's own MCP server wraps the sync.so API: take a video plus an audio track and regenerate the performer's mouth to match, with cost estimation before you spend, asset and project management, voice cloning, and TTS. Unlike avatar platforms that synthesize a presenter, this retimes lips on footage you already shot — the practical tool for dub passes, ADR fixes, and localized versions that keep the original take. Tools are generated from the Sync OpenAPI spec at startup, so new endpoints appear without a server update.

Connect

https://mcp.sync.so/mcp

claude mcp add sync -- npx -y @sync.so/mcp-server --api-key YOUR_API_KEY

{
  "mcpServers": {
    "sync-labs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.sync.so/mcp"
      ]
    }
  }
}

{
  "mcpServers": {
    "sync-labs": {
      "url": "https://mcp.sync.so/mcp"
    }
  }
}

Sample tools

Field notes

Official and MIT, and every install field above re-checked unchanged: the hosted endpoint takes OAuth in Claude web (no key needed), while stdio needs SYNC_API_KEY — or omit it and the server runs a device-auth flow, caching a token at ~/.config/sync/mcp-credentials.json. Node 18+. Pricing is the same on re-check — $5/month Hobbyist through $249/month Scale, per-second generation charges of roughly $0.04–0.05 on every tier, and caps on clip length (1 min at the bottom, 30 min at the top), concurrent jobs and voice clones — so call generate_estimate-cost before long renders; the pricing page pitches a free trial but lists no free plan. Models named there are still Lipsync-2-Pro, Sync-3 and React-1; ask models_get rather than assuming. Watch the surface mismatch: the repo README documents voices, tts and projects tools, but Sync's public API reference only covers generations, assets, models, estimate, batch and healthcheck — tools are generated from the live OpenAPI spec at startup, so read tools/list instead of trusting either list. The repo woke up (last pushed 7 Sep 2026, adding session and upload limits to the HTTP transport) but is still a 1-star project, and npm @sync.so/mcp-server sits at 0.1.4 from 16 Mar 2026 — tolerable only because the tool surface comes from the spec, not the package. Ethics and rights: relighting someone's mouth to say new words needs the performer's consent, and many jurisdictions and union agreements now require it explicitly.

Also in Avatars & Performance

Hedra MCP Serverpasie15

Character-3 talking-avatar video, TTS, and image generation through Hedra's API.

avatar-video · lip-synccredits

C CraftStory MCPCraftStory Official

Official CraftStory server: talking-avatar video from a photo and audio, plus short MiniMax H3 clips with sound.

avatar-video · talking-headremote · credits

AKOOL MCPAKOOL Official

Hosted MCP for AKOOL face swap, character swap, image-to-video, TTS and avatar lookup.

face-swap · character-swapremote · credits

Tavus MCPrakeshdavid

Phoenix replicas, persona videos, lipsync, and conversational AI via the Tavus API.

digital-twin · avatar-videofreemium

HeyGen Remote MCPHeyGen Official

Hosted MCP for avatar videos, lipsync, and 175-language video translation.

avatar-video · lip-syncremote · credits

bitHuman MCPbitHuman Official

Official bitHuman CLI server: build avatar agents from a face image and render WAV-driven talking video locally.

avatar-video · lip-syncremote · credits

Pairs well with

Artlist MCPArtlist Official

Official hosted Artlist MCP — generate images, video, music and voice-over on your Artlist credits.

text-to-image · text-to-videoremote · credits

BudgetPixel MCPBudgetPixel Official

Hosted OAuth MCP onto BudgetPixel's image, video, music, SFX and Topaz upscale catalogue.

text-to-video · image-to-videoremote · paid

C Cinegenta StudioCinegenta Official

Hosted screenplay-to-production MCP with free planning and quotes, then a greenlit run under a server-enforced cap.

screenplay-parsing · shot-breakdownremote · credits