Typecast for AI agents
Typecast generates expressive AI speech from text, used by content and product teams that need narration or voiceover without booking 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 Typecast.
Generate speech from text
Turn a script into narrated audio using a chosen voice.
List available voices
Pull the voice catalog as a read-only check before picking one for a project.
Get recommended voices for a script
Ask for voice suggestions that fit the tone of a given piece of text.
7 Typecast actions, graded by risk.
Every Typecast action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- typecast.get_voiceGet Voice
- typecast.list_voicesList Voices
- typecast.get_subscriptionGet Subscription
write
4Create and change things. Allow, or ask the user first.
- typecast.compose_speechCompose Speech
- typecast.generate_speechGenerate Speech
- typecast.recommend_voicesRecommend Voices
- typecast.generate_speech_with_timestampsGenerate Speech With Timestamps
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Typecast in three steps.
- 01Your users connect TypecastThey add their Typecast api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “compose Speech” can wait for the user to approve.
- 03Any agent can actYour agent calls Typecast through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('typecast', { read: 'allow', write: 'ask', // compose_speech destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Typecast connects.
Users add their Typecast 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 Typecast 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 Typecast from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Typecast and Arc0, answered.
Can I use Typecast with Claude, ChatGPT or Cursor?
Yes. Connect Typecast 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 Typecast actions you allow.
How do users connect Typecast?
Users add their Typecast 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 Typecast actions can my agent take?
7 in total: 3 read, 4 write and 0 destructive, such as “compose Speech”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Typecast?
Yes. Allow read actions and deny writes in the Typecast policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Typecast too?
Yes. The same Typecast connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Typecast into your agent.
Your users connect Typecast once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan