ASR + LLM + TTS
Choose models per agent or use the defaults. Six languages, with automatic switching mid-call.
The platform for developers: build your agent from the dashboard with a prompt, a language and tools that call your systems. Speech recognition, LLM and speech synthesis included. Hosted in Switzerland.
Screenshot della dashboard SwissAI: agente con prompt, SIP URI e tool HTTP
1600×1200 px · swissai-hero.jpgFrom the dashboard: name, language, prompt, models and the tools that call your HTTP endpoints.
Call the agent over WebRTC from the dashboard. Read the transcript and every tool call live.
Point your trunk or PBX at the SIP URI. The agent answers, talks and calls your tools.
Choose models per agent or use the defaults. Six languages, with automatic switching mid-call.
GET or POST endpoints on your side: the agent calls them with arguments extracted from the conversation.
Every agent has a SIP URI and can also be reached from the browser for testing and integration.
End-of-call webhook with transcript, duration and outcome. Full logs in the dashboard.
Infrastructure and data stay in Switzerland.
Built-in transfer tool: the agent hands the call over to a fallback number when needed.
Screenshot: trascrizione live di una chiamata di prova con le chiamate ai tool
2100×900 px · swissai-trascrizione.jpgPay for minutes, not seats. Free trial at swissai.dev.
Get started at swissai.dev