Cloud or on-premises · Open-source models

Enterprise voice AI you can also run inside your own data center

Voice agents, voice cloning, real-time conversations and analytics — delivered as a managed cloud or fully on-premises. Built on open-source models, so your data and voices never leave your perimeter.

No credit card · Free tier · Cancel anytime

One platform for every voice & agent workload

A complete enterprise suite — not a single API.

Agent Studio

Visual workflows, multi-agent handoff, tools, knowledge base.

Voice Studio

Voice cloning, prompt-to-voice, multi-voice agents.

Real-time Voice

Sub-second conversations with barge-in and interruptions.

Analytics

Per-agent ROI, sentiment, cost forecasting and reports.

Governance

RBAC, audit logs, PII redaction, GDPR / PDPL ready.

Multi-tenant

Workspaces, quotas, granular roles, SSO-ready.

Creative Suite

TTS, STT, dubbing, sound effects, music — all in one.

Bring your model

Plug in any open-source LLM, TTS or STT — your choice.

Where you run it is your choice

Cloud, On-Premises or Hybrid

Every model in our stack is open source, so the entire platform can run inside your own infrastructure — including fully air-gapped networks.

Managed Cloud

Multi-tenant cloud with autoscaling and a 99.9% SLA. Start in minutes.

  • ✓ Token-based pricing
  • ✓ Global edge network
  • ✓ SOC 2 + GDPR ready
Our advantage

On-Premises

Ship the entire stack into your data center, private cloud or air-gapped network. Your data never leaves your perimeter.

  • ✓ 100% open-source models
  • ✓ Docker, Kubernetes or bare-metal
  • ✓ Air-gapped + offline licensing
  • ✓ Bring your own GPUs (NVIDIA / AMD)
  • ✓ HIPAA, PDPL, GDPR, sovereignty

Hybrid

Run inference on-premises while we handle the management plane.

  • ✓ Sensitive workloads stay local
  • ✓ Centralised governance
  • ✓ Federated analytics

How we compare to other voice AI platforms

What enterprises actually need — versus what most cloud-only vendors ship.

Capability
Multi-tenant managed cloud
Fully on-premises deployment
100% open-source model stack
Per-user / per-agent quotas
Visual agent workflows
Self-hosted LLM routing
Audit logs + PII redaction
Bring-your-own GPUs
Other voice AI vendors
Yes
Rare — usually cloud only
Closed / proprietary
Workspace level only
Limited
Not supported
Add-on / limited
Not supported
OpenQlik
Native
Full air-gapped support
Yes — own the entire stack
Granular per-user / per-agent
Generally available
Llama / Mistral / Qwen routing
Built-in
NVIDIA + AMD ROCm

Comparison reflects publicly documented features of leading cloud-only voice AI vendors as of 2026.

Simple plans, model-aware pricing

Every plan includes a pool of credits. The credits you spend per minute depend on the model you choose — small models for cost-sensitive workloads, frontier models for the highest quality.

Starter

For pilots and small teams.

$99 / mo
  • ~ 1,500 voice minutes / mo*
  • Up to 5 seats
  • 2 agents
  • Email support
Get started
Most popular

Growth

For production teams.

$499 / mo
  • ~ 10,000 voice minutes / mo*
  • Up to 25 seats
  • Unlimited agents
  • Workflows
  • Priority support
Get started

Enterprise

For regulated and large teams.

Custom
  • Volume credits & SLAs
  • SSO + SAML
  • Audit logs + PII redaction
  • Dedicated CSM
Talk to sales

On-Premises

Annual licence — unlimited usage.

Custom
  • Air-gapped install
  • Bring your own GPUs
  • Open-source model stack
  • White-glove deployment
  • 24/7 dedicated support
Talk to sales

*Estimated minutes assume a low-cost model. Premium providers and frontier models cost more per minute — try the live calculator below for your exact numbers.

Live cost calculator

Estimate your monthly cost

Pick a provider and model, then adjust your expected usage. Numbers update live.

Premium voice quality. Industry-leading TTS and voice cloning.

Real-time voice agents

5,000
50025k50k100k
Estimated monthly cost
$900
/ month
ElevenLabs · Turbo v2.5 · $0.180 / min
At 5,000 min / mo across providers
ElevenLabs$450 – $1500
OpenAI$300 – $1600
Deepgram$200 – $250
Open source (on-premises)$60 – $190

Rates are list prices per active voice minute (blended LLM + TTS + STT where applicable), as of 2026. Actual cost depends on call length, language and traffic mix. On-premises eliminates per-minute fees in exchange for hardware and a one-time licence.