MCP · works with Claude
Drive the studio from inside Claude
Connect Vidsly and ask Claude in plain words — a narrated voiceover MP3 or a lip-synced animated presenter video comes back in the chat. The same voice catalog as the studio, no browser tab required.
- 500
- credits per presenter video
- Refunded if a render fails
- 51
- narration voices
- Native in 7 languages + OpenAI
- 13
- OpenAI voices
- Read all 16 languages
- 10
- characters per credit
- Voiceovers to MP3
01Setup
Three steps to connect
Get your API key
Create a key on your dashboard (starts with
ksk_live_) and pick a plan — each presenter video costs 500 credits.Add to claude_desktop_config.json
Claude Desktop → Settings → Developer → Edit Config, then paste (with your key):
Config file{ "mcpServers": { "vidsly": { "command": "npx", "args": ["-y", "vidsly-mcp"], "env": { "VIDSLY_API_KEY": "ksk_live_..." } } } }- MP3 · watch link
Just ask Claude
"Narrate this script in Aria's voice, then send me the MP3."
The file or watch link comes back in the chat. Voices, presenters and reference photos all work exactly like they do in the studio.
Under the hood — vidsly-mcp on npm, plus a plain REST API.
Using claude.ai in the browser? A no-install connector (sign in, no key) is coming soon.