What is AiPBX and what core technologies power it?

AiPBX is an open-source enterprise IP PBX uniting Asterisk 22, Nginx L4 ALPN stream multiplexing, PHP 8 MVC web management, a high-concurrency Go WebSocket chat daemon, and native Android (Kotlin) / iOS (Swift) softphones.

Is AiPBX truly 100% free and open source?

Yes. AiPBX is released under the permissive MIT license. There are zero license keys, zero per-user or per-extension recurring fees, and zero feature paywalls.

How do Passkeys (WebAuthn) and Google OAuth enhance PBX security?

Traditional passwords are prone to phishing and credential stuffing. AiPBX supports FIDO2 asymmetric cryptographic verification using Touch ID, Face ID, Windows Hello, and YubiKey, alongside Google Workspace corporate OAuth 2.0 single sign-on.

Why is Port 443 ALPN stream multiplexing critical for enterprises?

Firewalls at hotels, airports and client offices often block every port except 443. AiPBX carries the web portal, WebRTC calls from browsers and the mobile apps, chat and the TURNS media relay over that single port, so remote staff can still place and take calls. Desk IP phones and carrier trunks keep using the standard SIP ports (5060/5061).

Does Microsoft Teams Direct Routing require third-party hardware or SBCs?

No. AiPBX incorporates a built-in SIP TLS & SRTP gateway fully compatible with Microsoft Teams Direct Routing specifications, eliminating the need for expensive third-party SBC appliances.

Do the mobile softphone applications drain battery life?

Not at all. AiPBX native Kotlin and Swift apps utilize High-Priority Push Notifications (FCM / APNs) instead of sustaining battery-draining continuous background sockets. Battery consumption is practically zero.

How do supervisor listening and whispering work?

A user with the supervisor or admin role dials the code and then the extension: *90 listens silently, *91 talks to the agent only (the caller cannot hear), *92 joins the call as a third party. The same actions are available from the Listen / Whisper / Barge buttons on the call center board.

How can I install AiPBX on my server?

On a clean Ubuntu 26.04 LTS machine, run our one-liner turnkey script: curl -fsSL https://raw.githubusercontent.com/mahirgul/AiPBX/main/install.sh | sudo bash The installer compiles Asterisk 22 and configures Nginx stream, MariaDB, PHP 8, and Go chat automatically.

Cloud AI services (Plugin)

Plugin (ai-cloud / ai-voicemail): Optional plugins from the official catalog. Enable them under Integrations → Plugins (see Plugin system & developer guide).

AI → Cloud services (admin only) holds the accounts of cloud AI providers in one place and chooses, for each job and language, which engine AI features use: a local model of this server (see Local AI models) or a cloud provider.

A cloud engine sends audio or text to that provider. Check its terms and your data-protection duties (KVKK/GDPR) before choosing one. Local models keep everything on the server.

Providers

Provider	Speech	Speech to text	Language models	Embeddings	Free tier
Google AI Studio (Gemini, Gemma)		✓ (Gemini)	✓	✓	✓
OpenAI	✓	✓ (gpt-4o-mini-transcribe)	✓	✓
Microsoft Azure AI Speech	✓	✓			✓
Google Cloud Text-to-Speech	✓				✓
Amazon Polly	✓				✓
ElevenLabs	✓	✓ (Scribe)			✓
Deepgram		✓ (Nova-3)			✓
Groq		✓ (Whisper large v3 turbo)	✓ (Llama, Gemma, …)		✓
OpenRouter			✓ (hundreds of models)		some models
NVIDIA NIM (build.nvidia.com)			✓ (Llama, Nemotron, Qwen, DeepSeek …)		trial credits
Qwen (Alibaba Cloud Model Studio)			✓ (qwen-plus, qwen-turbo, qwen-max …)		✓ (new accounts)
OpenAI-compatible (own address)			✓ (any service with the OpenAI chat API)		—

Each card has the key fields, a link to get a key, a Test button (a cheap authenticated call that shows the provider's own error when the key is wrong) and this month's use: minutes of audio turned into text, characters spoken and language-model tokens (table ai_cloud_usage).

Keys are stored encrypted in sys_settings as ai_tts.<provider>.<field> — the names the Cloud TTS page used before, so existing accounts keep working. The Cloud TTS page now only shows the status of its providers and links here; changing keys needs the admin role.

Engine for each job

For speech, speech to text and the language model in Turkish, German and English, choose a running or downloaded local model or a configured cloud provider (ai_engine.<job>.<lang> in sys_settings, values local:<model id> or cloud:<provider>). AI features that come later (AI applications, voice requests) use these choices, so switching between local and cloud needs no other change.

Trying

AI → Local models → Try: speech to text lists the configured cloud providers next to the local models: record from the microphone or upload a WAV file, pick the language, and compare the text and the time each engine needs.

Language models

Large language models are not run on the PBX itself (most servers cannot carry them); they come from the providers above. They are used by:

AI applications — routing by speech and voice requests with Understanding: cloud model (AI applications),
voicemail as text — the one-sentence summary (below).

The model of Google AI, OpenAI, Groq and OpenRouter is fixed (a small, fast one: gemini-2.5-flash, gpt-4.1-mini, llama-3.3-70b-versatile, google/gemini-2.5-flash). For the three providers below the card has a Model field; Test sends one tiny chat request, so a wrong model name shows at once.

Provider	Address	Model (default)
NVIDIA NIM	`https://integrate.api.nvidia.com/v1`	`meta/llama-3.3-70b-instruct`; any model of build.nvidia.com, e.g. `qwen/qwen3-235b-a22b`
Qwen (Alibaba Cloud Model Studio)	international `https://dashscope-intl.aliyuncs.com/compatible-mode/v1` (default); mainland China `https://dashscope.aliyuncs.com/compatible-mode/v1`	`qwen-plus`
OpenAI-compatible	your address ending in `/v1`, e.g. `https://api.deepseek.com/v1`, `https://api.mistral.ai/v1`, `http://10.0.0.5:11434/v1` (Ollama on another server)	required; the key is optional

Voicemail as text

AI → Cloud services → Voicemail as text: a new voicemail is written down with the speech-to-text engine of the PBX's prompt language (a small local model such as Vosk or Whisper, or a cloud provider) and, if summary is ticked, summarised in one sentence by the language model of that language ("John Smith wants to move tomorrow's 10:00 meeting to Friday").

The voicemail e-mail gets both under the list of details: template variable {ai_text} of the voicemail template (E-mail → Templates; a changed template needs {ai_text} added).
The app notification shows the summary (or the start of the transcript) under the caller (Android 1.0.66).
My Phone → Voicemail and the mobile apps' voicemail list show it next to the message.

Each message is processed once (table voicemail_ai); the e-mail comes first and the push uses the result. Voicemail is handled by Asterisk's own user, which cannot read the AI keys, so the work is done by the portal on the same server (api/voicemail_ai.php, only from 127.0.0.1, signed). Nothing here can hold back the e-mail or the notification: when the engine fails, they go out without the text. With a cloud engine the recording (speech to text) or its text (summary) is sent to that provider.