Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Key features
Speech-to-text in nine languages with cloud fallback
Speech synthesis with 10 voices and zero-shot voice cloning
Phone numbers for inbound and outbound calls with single and bulk dialing
Voice cloning on Growth plan and above
Tool calling and cross-call memory
Runs on commodity CPUs without GPU acceleration
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
What makes it different
Voice agents at 4–5¢ a minute with speech recognition, language model and voice all included, below competitor platform fees alone
Models run on commodity CPUs without needing GPUs, enabling on-device and edge deployment
Supports nine languages including Iberian languages most platforms don't offer
Full voice pipeline runs on-premise with audio never leaving the environment
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Lokutor
Kairos