Fonoster is a conversational AI framework and multi-tenant communications platform as a service. It serves as a programmable voice gateway and SIP telephony platform, enabling the creation of voice-based assistants and automated communication workflows using large language models.
The project distinguishes itself through a vendor-agnostic speech integration engine that abstracts speech-to-text and text-to-speech providers. It features a multi-tenant architecture that isolates telephony resources and user identities into distinct organizational workspaces.
The system covers a broad range of telephony capabilities, including SIP trunk configuration, bidirectional audio streaming, and PBX functionality. It provides tools for call flow logic control, real-time call status monitoring, and the programmatic origination of outbound calls. Security is handled through role-based access control, token-based session authentication, and API key management.
The communication stack can be deployed on private infrastructure or orchestrated using Docker containers.