Features
Twilio PSTN Calls
Inbound and outbound phone calls via Twilio Voice + Media Streams.
WebRTC Browser Calls
Talk to agents directly from the browser with peer-to-peer audio.
Video Avatar
Optional lip-synced video avatar (HeyGen or Tavus) on WebRTC cascade calls.
WhatsApp Business
Voice calls and text messages via WhatsApp Cloud API.
SMS / Chat
Text-based conversations with agents via Twilio SMS or the Chat API.
Multi-Provider
Mix and match STT, LLM, and TTS providers per agent — Deepgram, OpenAI, Anthropic, ElevenLabs, Cartesia, Ollama.
Speech-to-Speech
Ultra-low latency (~300ms) via OpenAI Realtime or Gemini Live.
Tool Calling
Built-in tools (transfer, handoff, DTMF) + webhook tools + MCP servers.
Knowledge Base (RAG)
Upload documents with three retrieval modes: prompt, auto, and tool.
Agent Versioning
Publish immutable versions, auto-promote phone numbers, rollback instantly.
A/B Testing
Weighted traffic routing on phone numbers, deterministic by caller.
Post-Call Analysis
Automatic summary, sentiment, success evaluation, and structured extraction.
Server Events
Bidirectional hooks — call-init, function-call, call-end, transcript updates.
How It Works
A caller connects over any transport; TurnCall runs a per-call Pipecat pipeline in one of two modes and streams audio back. See Architecture for the full pipeline, call flows, and data model.Tech Stack
| Component | Technology |
|---|---|
| Framework | FastAPI + Uvicorn |
| Voice Pipeline | Pipecat 1.4 |
| Database | PostgreSQL + SQLAlchemy async + Alembic |
| Cache | Redis |
| Telephony | Twilio Voice + Media Streams |
| Browser | WebRTC (SmallWebRTCTransport) |
| Video Avatar | HeyGen / Tavus (Pipecat avatar services) |
| STT | Deepgram / OpenAI / ElevenLabs / Cartesia |
| LLM | OpenAI / Anthropic Claude / Ollama / OpenRouter / Any OpenAI-compatible |
| TTS | Deepgram / OpenAI / ElevenLabs / Cartesia |
| S2S | OpenAI Realtime / Gemini Live |
| Knowledge Base | pgvector + OpenAI embeddings |
| VAD | Silero |
| Turn Detection | Smart Turn V3 (local ONNX) |