awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
fonoster avatar

fonoster/fonoster

0
View on GitHub↗
7,997 stars·529 forks·TypeScript·MIT·27 viewsfonoster.com↗

Fonoster

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.

Features

  • Conversational AI Agents - Enables the creation of voice-based assistants using large language models for natural language interactions over telephony.
  • Bidirectional Audio Streaming - Establishes a two-way audio stream to send and receive real-time sound between a caller and a system.
  • Conversational Voice AI - Framework for building LLM-powered voice assistants that handle natural language interactions over telephony.
  • Real-Time Conversational AI Frameworks - Provides a real-time framework for building low-latency voice agents by integrating STT, LLM, and TTS.
  • Speech-to-Text Integrations - Integrates speech-to-text and text-to-speech vendors to translate audio streams for AI conversational agents.
  • Speech to Text Transcription - Provides automated transcription of spoken audio into written text via configured speech-to-text engines.
  • Text-to-Speech - Synthesizes written text into spoken audio using configurable voices to communicate with telephony users.
  • Speech Integration Engines - Ships a vendor-agnostic engine that connects third-party speech-to-text and text-to-speech vendors to audio streams.
  • Vendor Abstractions - Provides a vendor-agnostic abstraction layer for switching between various speech-to-text and text-to-speech providers.
  • Instant Streaming Playback - Streams synthesized speech and audio files back to callers in real-time via third-party vendors.
  • Automated Communication Services - Connects telephony services to the internet to create custom automated communication sequences.
  • Cloud Telephony Infrastructure - Provides a cloud-native infrastructure for hosting and orchestrating scalable communication services.
  • Telephone Number Mapping - Maps telephone numbers to addresses and utilizes geographic information to handle calls from the public network.
  • Multi-Tenant Communication Platforms - Manages isolated telephony resources and user identities for multiple distinct organizational workspaces.
  • Private Branch Exchanges - Provides tools to set up private branch exchange features for managing internal and external communications.
  • Outbound Call Initiators - Enables the programmatic initiation of outbound phone calls to specific numbers via SDKs or command-line tools.
  • Programmable Voice Applications - Enables creating automated communication workflows that control call flows and route calls via API.
  • Programmable Voice Gateways - Provides a cloud-native interface for routing calls and streaming bidirectional audio to integrate PSTN connectivity.
  • Programmatic Telephony Management - Provides a programmatic interface for managing telecommunications services and telephony configurations in browser and server environments.
  • PSTN Connectivity - Establishes connectivity to the public switched telephone network and SIP providers via trunks.
  • PSTN Integrations - Routes calls between internal endpoints and the public switched telephone network to connect agents with external callers.
  • SIP Endpoint Management - Allows registering and controlling devices like softphones and applications to initiate or receive calls.
  • SIP Protocol Routing - Uses the Session Initiation Protocol to manage call signaling, endpoint registration, and trunking.
  • SIP Trunk Configurations - Provides tools to establish connections with providers by mapping virtual numbers and configuring transport protocols.
  • Telephony Management Systems - Provides tools for configuring SIP trunks, managing endpoints, and routing traffic between networks.
  • Call Control Interfaces - Executes a sequence of voice commands to answer, dial, mute, or terminate phone calls based on logic.
  • Call Traffic Routing - Processes incoming and outgoing telephony traffic by linking phone numbers and SIP trunks to application logic.
  • Application Data Isolation - Implements software-level mechanisms to isolate tenant data and configurations within a shared platform instance.
  • Role-Based Access Control - Implements a security model that restricts system actions by assigning permissions to specific roles mapped to users.
  • User Identity Management - Maintains records for individual and service accounts organized into logical workspaces for administration.
  • Multi-tenant Isolation Policies - Implements a multi-tenant architecture that isolates telephony configurations and data into distinct organizational workspaces.
  • Communication Platforms as a Service - Implements a multi-tenant CPaaS that isolates telephony resources and users into distinct workspaces.
  • Conversational Behavior Policies - Provides settings for system prompts, greeting messages, and timeouts to govern AI agent interaction behavior.
  • Voice Activity Detection - Allows adjusting activation and deactivation thresholds to accurately detect when a caller starts or stops speaking.
  • External Server Connectivity - Provides connectivity to external servers allowing AI agents to utilize tools for data retrieval and remote command execution.
  • Telephony Domain Grouping - Organizes endpoints, routing policies, and access rules into logical domains to define communication boundaries.
  • Audio Recording - Captures the voice of calling parties and saves the resulting audio files to a storage system.
  • Internal Call Routing - Facilitates direct communication between registered endpoints within the same logical domain for internal calls.
  • Telephony Input Capture - Collects DTMF tones and speech events from callers for use in interactive voice response systems.
  • Virtual Number Mapping - Connects virtual phone numbers from telephony providers to voice applications using account credentials and tokens.
  • API Key Management - Allows the creation and configuration of API keys with specific permissions to secure programmatic requests.
  • Communication Encryption - Secures data transmission by implementing TLS certificates with automated issuance and renewal.
  • Key Generation - Creates unique access keys with specific roles to authorize programmatic access to workspace resources.
  • Organizational Resource Ownership - Tracks user or workspace ownership of specific assets to enforce access boundaries and organizational grouping.
  • Session Authentication - Establishes secure connections using credentials and tokens to maintain persistent user sessions.
  • Token Signature Verification - Validates digital signatures and claims on tokens using the RS256 algorithm to ensure authenticity.
  • Token-Based Authentication - Implements RS256 signed tokens to verify identities and maintain persistent API sessions.
  • Session Token Issuance - Generates short-lived access tokens, identity tokens, and long-lived refresh tokens to control session duration.
  • Identity Verification - Verifies user identity via passwords, multi-factor authentication, and external providers.
  • Resource Organization - Groups related telephony resources into isolated environments to manage access and collaboration.
  • Call State Monitoring - Provides real-time tracking of phone call states via event streams for connection and completion monitoring.
  • Protected Endpoints - Protects API endpoints using tokens and role-based access control to ensure authorized execution.
  • Backend and Infrastructure - Programmable telephony and communication platform.
  • Communication - Programmable APIs for SMS, voice, and video.
  • Communication APIs - APIs for managing SMS, voice, and video communication.
  • Web/API Interfaces - Listed in the “Web/API Interfaces” section of the Awesome Rtc awesome list.

Star history

Star history chart for fonoster/fonosterStar history chart for fonoster/fonoster

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with Fonoster

These projects share indexed features with Fonoster. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • vocodedev/vocode-corevocodedev avatar

    vocodedev/vocode-core

    3,693View on GitHub↗

    Vocode-core is a framework for building real-time conversational AI voice agents. It serves as a conversational orchestrator and pipeline that integrates speech-to-text, large language models, and text-to-speech services to enable low-latency voice interactions. The project features a provider-agnostic interface that allows for swappable speech and language model providers, including support for both cloud APIs and local binaries. It distinguishes itself through a specialized telephony integration layer that enables agents to be deployed across phone lines, WebRTC, and virtual meeting platfor

    Python
    View on GitHub↗3,693
  • getstream/vision-agentsGetStream avatar

    GetStream/Vision-Agents

    6,029View on GitHub↗
    Pythonagentic-aiagentsai
    View on GitHub↗6,029
  • elevenlabs/elevenlabs-pythonelevenlabs avatar

    elevenlabs/elevenlabs-python

    2,873View on GitHub↗

    This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of conversational AI agents. It enables the creation of lifelike spoken audio from text, the replication of human voices through custom cloning, and the deployment of real-time voice agents capable of interacting with external large language models. The library distinguishes itself through deep integration of conversational AI capabilities, including the design of agent personas and the execution of real-time actions via APIs. It supports professional-grade audio production thro

    Pythonartificial-intelligenceconversational-aitext-to-speech
    View on GitHub↗2,873
  • livekit/livekitlivekit avatar

    livekit/livekit

    19,358View on GitHub↗

    LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it

    Gogolangmedia-serversfu
    View on GitHub↗19,358
Compare all 30 related projects→

Frequently asked questions

What does fonoster/fonoster do?

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.

What are the main features of fonoster/fonoster?

The main features of fonoster/fonoster are: Conversational AI Agents, Bidirectional Audio Streaming, Conversational Voice AI, Real-Time Conversational AI Frameworks, Speech-to-Text Integrations, Speech to Text Transcription, Text-to-Speech, Speech Integration Engines.

Which projects share features with fonoster/fonoster?

Projects with overlapping indexed features include: vocodedev/vocode-core — Vocode-core is a framework for building real-time conversational AI voice agents. It serves as a conversational… getstream/vision-agents. elevenlabs/elevenlabs-python — This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of… livekit/livekit — LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with… pipecat-ai/pipecat — Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech… livekit/agents — This project is a framework for developing multimodal AI agents that function as programmable participants in…