Private voice AI infrastructure

Private voice AI runtime.

Run production voice agents on your own infrastructure. Bring your STT, LLM, TTS, carrier, and data plane. Pay providers directly. Keep every call boundary under your control.

Install your runtime

0% Aywa markup on provider minutes Local audio, transcripts, tools, secrets V2V realtime or cascade pipelines

Public demo runs on Aywa infra for evaluation only. Production traffic runs on the runtime you install.

One private runtime connects voice entrypoints to the providers and data plane you control.

Runtime integrations

Bring the providers your stack already trusts.

Native integrations, compatible APIs, BYO telephony, S3-compatible storage, observability sinks, and customer adapters can coexist inside the same private runtime.

LLM and reasoning

Model routes

OpenAI Azure OpenAI Anthropic Google Gemini Groq and more

Speech in

Streaming STT

Deepgram nova-3 AssemblyAI Gladia Speechmatics Soniox and more

Speech out

Voice routes

ElevenLabs Cartesia OpenAI TTS Deepgram Aura LMNT and more

Carrier edge

Telephony and media

BYO SIP Telnyx path FreeSWITCH Twilio path LiveKit WebRTC bridge and more

State and analytics

Runtime data plane

Postgres Redis / Valkey ClickHouse S3 MinIO and more

Ops and security

Production controls

API keys @aywa-ai/runtime-sdk Webhook signing Call leases and more

native, compatible, custom adapters · and more

Voice experience engine

Voice-to-voice runtime, optimized for the human turn.

The runtime is built around the real-time phone experience: listening, deciding when the user has finished speaking, streaming the model early, keeping TTS playable on telephony, and measuring latency across every stage without locking the deployment to one provider.

TM Voice-to-voice loop

Streaming STT, turn classification, model first-delta tracking, segmented TTS, barge-in, and media playout in one private call/session boundary.

VQ Voice quality

Telephony audio normalization, loudness leveling, soft limiter, speed adjustment, TTS continuity, and a single-output call mixer.

LT Latency controls

STT preconnect, streaming LLM first-delta tracking, segmented TTS playout, provider retries, fallback voices, and runtime SLO metrics.

WH Tools and webhooks

Function tools, native call controls, signed server messages, webhook outbox retries, redacted logs, and outbound request allowlists.

Why private runtime

For teams outgrowing hosted voice-agent constraints.

Hosted platforms are excellent for prototypes and managed launch speed. Aywa Runtime is built for teams that are ready to own the execution layer: cost model, capacity planning, provider routing, privacy boundary, and production debugging.

We describe infrastructure tradeoffs as a product category. Aywa Runtime is independently developed and does not imply affiliation with any third-party voice platform.

CM Cost model clarity

License the runtime separately and keep STT, LLM, TTS, telephony, storage, and analytics billing with the providers you choose.

CP Capacity under your control

Scale on your VPS, cloud, or Kubernetes design instead of treating every concurrency decision as a hosted-plan constraint.

DB Explicit data boundary

Audio, transcripts, recordings, tool payloads, provider secrets, and runtime logs stay in the infrastructure you operate.

DX Production debugging

Inspect calls from inside the runtime: provider timing, endpointing, tool attempts, webhook retries, and redacted support bundles.

Architecture

Control plane outside. Runtime inside your infrastructure.

The SaaS manages licensing, releases, instance health, and migration workflows. The call path, provider secrets, recordings, and telephony edge stay in the customer deployment.

Aywa SaaS Control plane

License server signed activation, grace period

Private registry signed images, stable channel

Migration center imports, mappings, dry-runs

Customer VPC / VPS / Kubernetes Private runtime plane

Voice ingress SIP trunk Carrier adapter paths WebRTC bridge

aywa runtime Real-time turn engine

STT, LLM streaming, TTS, barge-in, tools, webhooks, retries, and call state stay in process.

Turn manager Tool runner Webhook outbox Fallbacks

BYO providers LLM native, compatible, or custom Streaming STT with adapter fallbacks Low-latency voices and custom TTS

Postgres assistants, calls, config

Redis leases, realtime state

Analytics sink ClickHouse or your observability stack

S3 / R2 / MinIO recordings and artifacts

No audio or transcripts in Aywa SaaS Provider secrets remain local Support bundles redact by default

Deployment

One command for trials. Hardened paths for production.

Start on one VPS with the Standard runtime, then move to Enterprise when Aywa needs to help with multi-runtime, HA, load balancing, or custom release channels.

api.aywaruntime.com

curl -fsSL https://api.aywaruntime.com/v1/installer | \
  sudo AYWA_INSTALL_TOKEN="$AYWA_INSTALL_TOKEN" \
  RUNTIME_PUBLIC_URL="https://runtime.example.com" \
  AYWA_RUNTIME_IMAGE="$AYWA_RUNTIME_IMAGE" \
  bash

aywa status
aywa update --channel stable
aywa support-bundle --redact

Private runtime pricing

One production runtime slot. Enterprise when you need more.

Standard is a single licensed private runtime installed on your infrastructure. Aywa charges the runtime license; STT, LLM, TTS, telephony, storage, and analytics stay with your provider accounts, so usage is paid at source with no Aywa platform markup on call minutes.

Runtime license prices exclude applicable taxes. Stripe applies configured VAT or local tax registrations at checkout from the billing address and business tax ID when provided.

Additional Runtime Slots, volume pricing, HA, load balancing, private builds, and accompanied installs are Enterprise custom.

Trial

$0 / 14 days

No credit card required for qualified technical evaluations.

One Runtime Slot to validate deployment, import flow, provider credentials, voice-to-voice calls, and call quality.

1 private Runtime Slot
Installer and Docker Compose
Trial license token

Start trial

Standard

$49 / mo

One production Runtime Slot. $49/month or $490/year, before applicable taxes.

For one production deployment with the runtime dashboard on customer infrastructure and provider costs paid directly.

1 production Runtime Slot
Stable release channel
Open Runtime Dashboard from app.aywaruntime.com

Choose Standard

Enterprise

Custom

Volume pricing for multiple Runtime Slots.

For teams that need multi-runtime, HA, load balancing, private builds, SLA, or installation led by Aywa.

Custom Runtime Slots and groups
Managed Edge / HA architecture
Private release policies

Contact sales

Enterprise path

When one runtime slot is not enough, we design the deployment with you.

Standard stays intentionally simple: one licensed runtime, installed by the customer. Enterprise is for teams that need multiple runtimes, private release policies, HA/edge design, procurement, security review, or an accompanied production cutover.

Contact sales Start Standard first

Fit criteria

Use Enterprise for architecture, not just volume.

We scope runtime topology, rollout gates, provider routing, support boundaries, and operational ownership before any custom contract.

HA HA and edge design

Customer-owned load balancer, SIP/media edge choices, failover expectations, and runbook ownership.

PB Private builds

Pinned releases, private channels, rollout windows, and signed images for controlled environments.

MS Migration support

Import mapping, provider credential plan, phone-number cutover, and validation calls before traffic.

SR Security review

Data boundary, support bundle policy, access model, audit events, and deployment evidence package.