Aivoov for AI agents
AiVOOV is a text-to-speech platform that converts written text into natural-sounding voiceovers across many voices and languages. Content creators use it to produce narration without a studio. 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 Aivoov.
List available voices
Browse the catalog of text-to-speech voices and languages available before generating a voiceover.
Pick a voice for a script
Select a specific voice matching a target language and tone for a voiceover project.
Check voice language coverage
Confirm a needed language is supported among the available voices before committing to a script.
1 Aivoov actions, graded by risk.
Every Aivoov action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- aivoov.list_voicesList Voices
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Aivoov in three steps.
- 01Your users connect AivoovThey add their Aivoov api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Aivoov through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('aivoov', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Aivoov connects.
Users add their Aivoov 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 Aivoov 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 Aivoov from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Aivoov and Arc0, answered.
Can I use Aivoov with Claude, ChatGPT or Cursor?
Yes. Connect Aivoov 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 Aivoov actions you allow.
How do users connect Aivoov?
Users add their Aivoov 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 Aivoov actions can my agent take?
1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Aivoov?
Yes. Allow read actions and deny writes in the Aivoov policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Aivoov too?
Yes. The same Aivoov connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Aivoov into your agent.
Your users connect Aivoov once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan