Gan.AI for AI agents
Gan.AI provides text-to-speech, voice cloning, and video personalization APIs for creating natural, expressive speech and video, used by marketing teams personalizing outreach at scale. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Gan.AI.
Generate speech from text
Convert a script into speech audio for a personalized outbound video or message.
Check a video inference's status
Get an avatar video inference's status before sharing the finished personalized video.
Read-only avatar library checks
List photo avatars as a read-only step before choosing one for a new video.
8 Gan.AI actions, graded by risk.
Every Gan.AI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- gan_ai.list_avatar_videosList avatar video inferences
- gan_ai.list_photo_avatarsList Photo Avatars
- gan_ai.get_photo_avatar_detailsGet Photo Avatar Details
- gan_ai.list_photo_avatar_inferencesList photo avatar inferences
- gan_ai.get_avatar_video_inference_detailsGet Avatar Video Inference Details
- gan_ai.get_photo_avatar_inference_detailsGet photo avatar inference details
write
2Create and change things. Allow, or ask the user first.
- gan_ai.ttsGAN AI Text-to-Speech
- gan_ai.loginLogin
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Gan.AI in three steps.
- 01Your users connect Gan.AIThey add their Gan.AI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “gAN AI Text-to-Speech” can wait for the user to approve.
- 03Any agent can actYour agent calls Gan.AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('gan_ai', { read: 'allow', write: 'ask', // tts destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Gan.AI connects.
Users add their Gan.AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Gan.AI connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Gan.AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Gan.AI and Arc0, answered.
Can I use Gan.AI with Claude, ChatGPT or Cursor?
Yes. Connect Gan.AI to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Gan.AI actions you allow.
How do users connect Gan.AI?
Users add their Gan.AI api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Gan.AI actions can my agent take?
8 in total: 6 read, 2 write and 0 destructive, such as “gAN AI Text-to-Speech”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Gan.AI?
Yes. Allow read actions and deny writes in the Gan.AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Gan.AI too?
Yes. The same Gan.AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Gan.AI into your agent.
Your users connect Gan.AI once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan