Conversational Voice Assistant
100% Offline AI Voice Pipeline
A complete real-time voice assistant running entirely on your own GPU — ASR → LLM → TTS with sentence-by-sentence streaming and instant barge-in.
Qwen3-ASR transcribes, llama.cpp runs Gemma 4 12B QAT with MTP speculative decoding (148 tok/s), Supertonic 3 synthesises speech, and a WebSocket streams audio back — all without a single packet leaving your machine.
From Microphone to Voice, On One GPU
Five stages, zero cloud. Each block runs locally on an NVIDIA RTX 4080 (16 GB VRAM) and chains into the next over a WebSocket.
Stage 1
Qwen3-ASR 0.6Basistente.pipe.asr.desc
Stage 2
Gemma 4 QAT + MTPasistente.pipe.llm.desc
Stage 3
Supertonic 3 ONNXasistente.pipe.tts.desc
Stage 4
WebSocket binaryasistente.pipe.streaming.desc
Stage 5
Silero VADasistente.pipe.bargein.desc
E2E Latency (MTP)
VRAM / Session
TTS Engines
Offline
What Makes It Different
Not a wrapper around a cloud API — a full voice stack that runs on a single GPU
Total Privacy
100% offline. Audio, transcripts and models never leave your hardware. No vendor, no leak surface, full European data sovereignty.
Complete Pipeline
ASR → LLM → TTS → streaming → barge-in, end-to-end in one codebase. No gluing five SaaS together — every stage is yours.
Multi-TTS
Five interchangeable engines: Supertonic 3 (production), Kokoro 82M (lowest latency, RTF 0.02), edge-tts (online), Piper and Qwen3-TTS (offline, high quality).
Real-time Barge-in
Neural Silero VAD detects the user speaking over the assistant and interrupts playback instantly — natural turn-taking, not walkie-talkie.
Integrated CRM & Signing
Glassmorphism frontend with live chat transcript, customer CRM panel and AES digital signature via Signaturit (SMS OTP).
MTP Speculation
Gemma 4 QAT + a 242 MB MTP drafter verify tokens speculatively — 148 tok/s vs 84 tok/s without MTP, a 75% speedup.
Pricing
Open core for non-commercial use, commercial licence for production deployments
Core
Research, education & hobby
- Full ASR → LLM → TTS pipeline
- 5 swappable TTS engines
- WebSocket streaming + barge-in
- Frontend with CRM & digital signature
- Complete source code
Enterprise
Multi-tenant outbound
- Everything in Core
- Native multi-tenant (PostgreSQL + Redis)
- Concurrent outbound calls (10+)
- SIP trunking / real telephony
- Dual legal compliance
- On-premise deployment
Custom
Tailored deployment
- Everything in Enterprise
- Custom CRM / dialer integrations
- Fine-tuned models (LoRA / QLoRA)
- Additional languages & accents
- 24/7 SLA support
Want a voice assistant that never phones home?
Self-hosted. Offline. European. Clone the PolyForm Noncommercial core, or talk to us about a multi-tenant production deployment.