Latency
Conversations without the wait
~0.9 sp50
1.2 sp95
Measured from end of turn to first agent audio on the fast profile.
Voice agent API
Build voice agents that respond naturally. Not expensively.
Real-time conversational AI with natural voices, custom agents, memory and tool calling. One simple API, no audio infrastructure to run. Pay per turn, not per minute.
- Echo cancellation (AEC)
- Voice detection (VAD)
- Noise suppression (NS)
- Auto gain (AGC)
- Barge-in on by default
~0.9 smedian reply (p50)
$0.003per turn, Fast tier
~50stock voices + cloning
Live demo
Talk to a Ciabatta agent
A short call with a sample agent. Uses your microphone; nothing is recorded or stored.
Ready
Try asking:
"What can you do?"
"How fast can you reply?"
"Interrupt me mid-sentence"
Pricing
Pay for conversation, not silence
$0.003per turn (Fast)
$0.13per idle hour
Billed per agent turn, so listening time is almost free. See pricing
Control
Your agents. Your rules.
- ~50 voices or clone your own
- Model tier per agent
- Webhook, client and built-in tools
- Per-customer memory
- Custom personality and instructions
Built in
Built for real conversations
The audio pipeline is handled for you. No WebRTC stack, no echo tuning, no VAD to wire up.
Echo cancellation
Server-side AEC, fed with the exact audio the caller hears.
Barge-in, on by default
Talk over the agent and it stops immediately. Or duck instead.
Voice detection
Built-in VAD and turn detection decide when the caller is done.
Noise suppression + AGC
Cleans up background noise and evens out quiet or loud mics.
Tools
Webhook, client and built-in tools.
Memory
Per-customer conversations and summaries, with your retention settings.
Resilient connections
Dropped connections resume with no lost or repeated audio.
Natural voices
Nearly 50 stock voices, plus cloning from a short recording.
Agent Studio
Configure an agent in a few clicks
Set the voice, model, tools, memory and personality from the dashboard, or do it all through the API. Changes are versioned, so you can test safely.
Warm, friendly Preview
S FastML
You are a concise, upbeat support agent for a bakery. Confirm orders before booking.
check_hoursbook_slottransfer_call
Remember each customer
Developers
Ship in minutes
Create a session on your server, hand the WebSocket URL and token to your web or mobile app, and you have a talking agent.
// npm install @getciabatta/sdk
import { Ciabatta } from "@getciabatta/sdk";
const ciabatta = new Ciabatta({ apiKey: process.env.CIABATTA_API_KEY });
const session = await ciabatta.sessions.create("support", { customer_id: "cust_123" });
// hand session.ws_url + session.token to your web or mobile appPricing
Your cost advantage, calculated
Prepaid credits, no minimums. Every turn reports its usage.
Ciabatta-
Example competitor-
Estimated savings-
Illustrative monthly estimate at 3.5 turns per minute, using the Ciabatta per-turn price for the selected tier (- per turn, - per minute) against an illustrative competitor price of $0.10 per minute. Actual costs vary with turns, allowances, model choices and surcharges.
| Model tier | Per turn | ~Per min |
|---|---|---|
| S (fastest, default) | $0.0030 | ~$0.011 |
| M | $0.0045 | ~$0.016 |
| L | $0.0065 | ~$0.023 |
Included in every turn
- 6,000prompt tokens
- 400output tokens
- 400speech characters
- 45 sconnected time
Need more? A turn can always use extra tokens, characters or time for an additional fee: prompt and output tokens past the allowance at 1.5x the model's list price, speech at $0.0003 per 100 extra characters, and connected time past the allowance at $0.13 per hour. Nothing gets cut off.
See the same usage at other platforms
Competitor costs use the typical all-in per-minute ranges below (light bar = high end of the range).
| Platform | Typical all-in price | Billing |
|---|---|---|
| Ciabatta | $0.011-0.037/min | Per turn; idle listening $0.13/h |
| Vapi | $0.10-0.30/min | Per minute + providers |
| Retell AI | $0.10-0.20/min | Per minute |
| ElevenLabs Agents | ~$0.08-0.10/min | Per minute, plan-bound |
| Bland | ~$0.09/min | Per minute |
| OpenAI Realtime | ~$0.10-0.30/min | Per audio token |
Competitor prices are approximate public list prices as of October 2026 and vary by plan and provider choice.
Start building for free
New accounts get free signup credit. Build an agent, pick a voice and talk to it in the Playground in a few minutes.