Sonic-fast TTS purpose-built for real-time voice agents.
Cartesia's Sonic model targets the latency frontier — sub-100ms first-byte streaming TTS that pairs beautifully with Deepgram + a fast LLM for end-to-end response under 600ms. Callplane ships native Sonic support as a first-class TTS adapter.
A voice AI assistant is only useful when it can connect to the rest of your stack. The Cartesia integration helps Callplane fit into the systems your team already uses for calling, transcription, reasoning, speech, routing, or customer data. That means the assistant can move from a demo into a production workflow without forcing you to replace your existing tools.
Callplane keeps the integration flexible. You can run one assistant with Cartesia, pair it with other providers for a full voice pipeline, and change providers later if your cost, latency, coverage, or quality requirements change. This is especially useful for teams that need different settings per assistant, region, campaign, or customer segment.
The result is a voice agent that is easier to operate: fewer hard-coded assumptions, clearer provider boundaries, and a pricing model that separates Callplane's platform fee from the third-party services you already trust.
Choose Cartesia when latency is the ceiling on user experience and you can trade a small amount of voice character for speed. Choose ElevenLabs when voice quality and emotion are the differentiator.
# .env
CARTESIA_API_KEY=...
# Per-assistant config:
# TTS -> Provider: Cartesia
# Model: sonic-3.5
# Voice: 79f8b5fb-2cc8-479a-80df-29f7a7cf1a3eFor full setup, see the docs.
Callplane: $0.03/min platform fee. Cartesia: per-character pricing, typical voice agent ~$0.03/min. Significantly cheaper than ElevenLabs while delivering best-in-class latency. BYO mode passes Cartesia rates through unchanged.