Image generation
Text-to-image in 16:9, 9:16, or 1:1 - up to 4 variations per call. Condition on one reference image, or several labelled ones for character and style consistency.
Connect Dolphin AI to Claude, Cursor, or any MCP client. Images, video, long-form video, and speech - one URL away.
Connect once, generate from any conversation.
In the Claude app or on claude.ai, go to Settings → Connectors and choose Add custom connector.
Open Claude settingsClick Add Custom connector and paste the URL - https://mcp.trydolphin.ai/mcp

Authenticate with your Dolphin AI Studio account. Ask Claude to generate an image or video.
Your AI agent handles everything - model selection, polling, delivery.
Generate a cinematic 16:9 video of a drone shot over a misty forest at sunrise, about 6 seconds.
Task registered with an ETA. The agent returns the finished clip as a downloadable URL.
Everything you need to generate media programmatically.
Text-to-image in 16:9, 9:16, or 1:1 - up to 4 variations per call. Condition on one reference image, or several labelled ones for character and style consistency.
Text-to-video and image-to-video with first/last frame control. 480p to 1080p. Most models run 4–10s, a few up to 15s.
One script, one reference image, one talking video - 30 seconds to several minutes, speech generated automatically. Always 9:16.
Any text, spoken - pick a voice from a full catalogue with previews, accents, and use-case labels.
Guide generation with labelled reference media - image for most models, plus video and audio on Seedance 2.0.
Register a task, get an ETA, poll for status - or skip the polling and get the finished asset back in one call.
Same credits, same workspace balance as Dolphin AI Studio. Check the cost upfront, or see it returned with the result.
Pin a default model and voice once - they persist across conversations, so calls that skip a model just work.
OAuth for web agents, API key for CLI. No credentials to manage in your prompts.