Boilerplate-free voice agents.
Define a prompt, register Python functions as client tools, deploy — across three voice-agent backends. minmo handles JSON-Schema generation and each provider's REST API, so you write configuration once instead of translating provider payloads.
Same code · three provider towers
Why minmo
- Zero boilerplate
-
One decorator turns a typed Python function into a client-tool
schema. One
deploy()call publishes it. - Provider-agnostic
-
The same
VoiceAgentAPI works across AssemblyAI, Hume, and ElevenLabs — three backends that don't share a wire protocol. - Fail fast, explain
-
Typed errors and a plain-language
"info"string on everydeploy()result: what happened, what to do next. - Test without spending
-
simulate()runs your tool logic against any OpenAI-compatible LLM — no live voice session, no burned minutes.
Cleared for