Cost $0.000
Session Cost
$0.000
STT$0.000
LLM$0.000
TTS$0.000
Effective rate$0.000/min
Computed from real usage (LLM tokens, TTS characters, audio minutes) at configurable list rates.
Latency —
Voice-to-Voice Latency
—
Transcription (STT)—
Inference (LLM)—
Speech Gen (TTS)—
Per turn only (not cumulative): time from you finishing speaking to the first bot audio. Rows are per-service time-to-first-byte. Long replies / tool calls raise the headline number.
Tokens 0
LLM Token Usage
0
Prompt tokens0
Completion tokens0
TTS characters0
Actual usage reported by the model, accumulated over this session.
Duration —
🎙️
Click Connect in the top toolbar to start real-time audio interaction.
Your selected LLM, STT, TTS, Voice, and Language will be active — switch any of them mid-call and the call restarts with the new setup.
💬
Text Chat
Chat with the selected LLM directly over text — no voice pipeline. Type a query below to begin.
📋
No conversations saved yet. Conversations auto-save when you disconnect or clear.
Status
Client
Disconnected
Agent
Disconnected
Audio Activity
Bot
You
silent
Active Config
Scenario—
LLM—
STT—
TTS—
Voice—
Language—
KB—
Reservation API—
Session
TransportSmall WebRTC
Session ID—
Duration—