Conversation Playground

Talk to an AI voice agent. Full STT → LLM → TTS pipeline with real-time streaming and latency stats.

Engines & prompt

Off = faster answers. On = better reasoning but slower, and some models may return an empty reply.

Type a message or press the microphone button below to start.

Ready
Latency
STT
—
LLM first token
—
LLM total
—
TTS
—
Total
—
Turn history
No turns yet.
Token Usage
Promptn/a
Completionn/a
Totaln/a

No turns yet.