LMNT for AI agents
LMNT is a text-to-speech API that generates and manages custom AI voices for creative and technical audio applications, from voiceovers to IVR systems. 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 LMNT.
Synthesize speech from text
Generate a speech audio clip from a script for a voiceover draft.
Check available voices
List the voices available on the account before choosing one for a project, read-only.
Approve before deleting a voice
Require approval before deleting a custom voice, since any project using it would lose access.
8 LMNT actions, graded by risk.
Every LMNT 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.
- lmnt.get_accountGet Account
- lmnt.get_voice_infoGet Voice Info
- lmnt.get_voices_listGet Voices List
write
4Create and change things. Allow, or ask the user first.
- lmnt.create_voiceCreate Voice
- lmnt.update_voiceUpdate Voice Info
- lmnt.synthesize_speechSynthesize Speech
- lmnt.generate_speech_with_metadataGenerate Speech With Metadata
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- lmnt.delete_voice_infoDelete Voice Info
LMNT in three steps.
- 01Your users connect LMNTThey add their LMNT api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Voice” can wait for the user, and “delete Voice Info” can be denied outright.
- 03Any agent can actYour agent calls LMNT through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('lmnt', { read: 'allow', write: 'ask', // create_voice destructive: 'deny', // delete_voice_info }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How LMNT connects.
Users add their LMNT 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 LMNT 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 LMNT from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
LMNT and Arc0, answered.
Can I use LMNT with Claude, ChatGPT or Cursor?
Yes. Connect LMNT 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 LMNT actions you allow.
How do users connect LMNT?
Users add their LMNT 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 LMNT actions can my agent take?
8 in total: 3 read, 4 write and 1 destructive, such as “create Voice”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in LMNT?
Yes. Actions like “delete Voice Info” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call LMNT too?
Yes. The same LMNT connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug LMNT into your agent.
Your users connect LMNT 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