# vocodedev/vocode-core

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/vocodedev-vocode-core).**

3,693 stars · 651 forks · Python · mit

## Links

- GitHub: https://github.com/vocodedev/vocode-core
- Homepage: https://vocode.dev
- awesome-repositories: https://awesome-repositories.com/repository/vocodedev-vocode-core.md

## Description

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 platforms.

The framework covers a broad range of capabilities including agent orchestration with custom personas and tool assignments, real-time audio streaming with interruption handling, and comprehensive telephony management for inbound and outbound call lifecycles. It also includes speech processing tools for multi-language transcription, synthetic voice cloning, and event-driven webhooks for monitoring call milestones.

## Tags

### Artificial Intelligence & ML

- [Voice Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents.md) — Provides a framework for building agents that use speech-to-text and text-to-speech for real-time voice interactions. ([source](https://docs.vocode.dev/agents.md))
- [Conversational Voice AI](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-voice-ai.md) — Serves as a conversational orchestrator that coordinates real-time audio streaming, LLM reasoning, and tool execution.
- [Real-Time Conversational AI Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/real-time-conversational-ai-frameworks.md) — Provides a complete framework for building low-latency voice agents by integrating STT, LLM, and TTS. ([source](https://docs.vocode.dev/open-source/what-is-vocode.md))
- [Conversational Audio Streams](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech/conversational-audio-streams.md) — Coordinates real-time audio data flow between speech-to-text, reasoning engines, and text-to-speech for low-latency voice interactions.
- [Agent Tool Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/ai-agents/agent-tool-definitions.md) — Implements mechanisms for defining custom agent tools, including names, parameters, and validation logic for live conversations. ([source](https://docs.vocode.dev/walkthrough_intro.md))
- [Conversational Interaction Settings](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-orchestration-settings/conversational-interaction-settings.md) — Enables configuration of prompts, languages, and voice providers to define how agents interact with users. ([source](https://docs.vocode.dev/api-reference/agents/create-agent.md))
- [Agent Persona Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-persona-configurations.md) — Defines personas and behavioral traits to govern the identity and conversational style of voice agents. ([source](https://docs.vocode.dev/walkthrough_intro.md))
- [Tool Assigners](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-tooling/tool-assigners.md) — Provides interfaces for linking specific functional tools, such as call termination or API triggers, to agents. ([source](https://docs.vocode.dev/configuring-number.md))
- [Agent Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-configurations.md) — Provides structured settings and configuration for defining AI agent behavior, providers, and operational parameters. ([source](https://docs.vocode.dev/configuring-number.md))
- [Conversational Turn Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-agents/conversational-turn-detection.md) — Implements logic to analyze speech context and determine when a user has finished speaking or interrupted the agent.
- [Conversational Behavior Policies](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-agents/conversational-turn-detection/conversational-behavior-policies.md) — Provides structured flows and policies to govern the behavior, greetings, and response parameters of conversational LLMs. ([source](https://docs.vocode.dev/agents.md))
- [Multi-turn Interaction Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-agents/conversational-turn-detection/multi-turn-interaction-managers.md) — Manages stateful conversations and turn-based interaction logic. ([source](https://docs.vocode.dev/open-source/turn-based-conversation.md))
- [Phone Call Handlers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/phone-call-handlers.md) — Provides agents capable of conducting natural language interactions and executing tasks over traditional phone lines. ([source](https://docs.vocode.dev/welcome.md))
- [Realtime Voice Conversation Facilitators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/realtime-voice-conversation-facilitators.md) — Facilitates low-latency, two-way spoken interactions with integrated emotion tracking. ([source](https://docs.vocode.dev/welcome.md))
- [Voice Activity Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/voice-activity-detection.md) — Implements automated identification of speech segments to manage conversational turn-taking. ([source](https://docs.vocode.dev/open-source/conversation-mechanics.md))
- [Agent Prompt Templates](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/configuration-and-specifications/agent-prompt-templates.md) — Implements reusable system prompt structures to govern the personality, goals, and reasoning of voice agents. ([source](https://docs.vocode.dev/configuring-number.md))
- [Agent Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-execution.md) — Provides mechanisms for agents to invoke external functions and tools, such as email or scheduling, during live conversations. ([source](https://docs.vocode.dev/open-source/agents-with-actions.md))
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Provides unified interfaces for specifying and configuring different large language model providers to power agent responses. ([source](https://docs.vocode.dev/open-source/langchain-agent))
- [AI Telephony Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-telephony-systems.md) — Manages inbound and outbound phone calls and provisions numbers for AI voice agents.
- [Language Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations.md) — Provides adapters and streaming interfaces to connect voice agents to various hosted or local language model providers. ([source](https://github.com/vocodedev/vocode-core/blob/main/roadmap.md))
- [Multilingual Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription/multilingual-transcription.md) — Supports multi-language audio transcription using configurable models to enable global voice interactions. ([source](https://docs.vocode.dev/open-source/language-support.md))
- [Real-Time Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription/real-time-transcription.md) — Provides instantaneous conversion of live microphone audio streams into text transcripts for real-time processing. ([source](https://docs.vocode.dev/open-source/playground.md))
- [Conversational Voice Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-voice-pipelines.md) — Coordinates a real-time pipeline of transcription, reasoning, and synthesis for continuous voice interaction. ([source](https://docs.vocode.dev/open-source/python-quickstart.md))
- [Function Calling Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/function-calling-interfaces.md) — Implements systems that enable language models to execute external tools and API functions based on model output. ([source](https://docs.vocode.dev/open-source/action-phrase-triggers.md))
- [Model-Driven Action Triggering](https://awesome-repositories.com/f/artificial-intelligence-ml/model-driven-action-triggering.md) — The project runs agent actions based on the model's determination using prompts and tool descriptions. ([source](https://docs.vocode.dev/action-triggers.md))
- [Real-Time Speech Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/real-time-speech-processing/real-time-speech-transcription.md) — Coordinates a pipeline of speech-to-text, LLMs, and text-to-speech for live audio interactions.
- [Speech Service Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-service-integrations.md) — Connects to both speech-to-text and text-to-speech providers to enable full audio-text-audio conversion. ([source](https://docs.vocode.dev/welcome.md))
- [Speech-to-Text Conversions](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-to-text-conversions.md) — Transforms real-time audio streams into machine-processable text using both cloud providers and local models. ([source](https://docs.vocode.dev/open-source/using-transcribers.md))
- [Speech Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-transcription.md) — Converts spoken audio to text using local model files and shared libraries for offline processing. ([source](https://docs.vocode.dev/open-source/local-conversation.md))
- [Text-to-Speech](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech.md) — Implements a system for synthesizing natural human speech from text input using various provider models. ([source](https://docs.vocode.dev/open-source/using-synthesizers.md))
- [Asynchronous Pipeline Coordination](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech/conversational-audio-streams/asynchronous-pipeline-coordination.md) — Coordinates speech recognition, response generation, and synthesis to manage asynchronous audio streams. ([source](https://docs.vocode.dev/open-source/how-it-works.md))
- [Tool Calling](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling.md) — Provides mechanisms for language models to request and execute external functions or scripts to perform real-time actions.
- [Voice Assistants](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-assistants.md) — Allows the definition of agent personas, system prompts, and synthetic voice characteristics.
- [Local Agent Deployments](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-deployment/local-agent-deployments.md) — Executes real-time voice conversations on local hardware to ensure privacy and low latency. ([source](https://docs.vocode.dev/open-source/local-conversation.md))
- [Agent Instantiation](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-orchestration-frameworks/agent-instantiation.md) — Implements mechanisms to create active agent instances based on specific configuration for custom behavior integration. ([source](https://docs.vocode.dev/open-source/agent-factory.md))
- [Multi-Provider Swapping](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/realtime-speech-to-speech-agents/speech-to-text-provider-selection/multi-provider-swapping.md) — Provides a swappable interface to switch between different speech-to-text, text-to-speech, and language model services. ([source](https://docs.vocode.dev/open-source/what-is-vocode.md))
- [Phrase-Based Action Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents/voice-activity-detection/wake-word-detection/custom-phrase-detection/phrase-based-action-execution.md) — Executes specific behaviors and controls conversation flow after the agent speaks a predefined phrase. ([source](https://docs.vocode.dev/action-triggers.md))
- [Custom Agent Flow Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-definitions/custom-agent-flow-definitions.md) — Allows developers to define custom response logic by subclassing a base agent class for real-time conversations. ([source](https://docs.vocode.dev/open-source/create-your-own-agent.md))
- [Reasoning Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/llm-model-integrations/reasoning-pipelines.md) — Connects agents to multi-stage prompting chains to enable retrieval augmented generation and complex decision making. ([source](https://docs.vocode.dev/open-source/langchain-agent.md))
- [Hybrid Local-Remote AI Routing](https://awesome-repositories.com/f/artificial-intelligence-ml/hybrid-local-remote-ai-routing.md) — Routes audio and text processing tasks between local binaries and cloud APIs to balance latency and connectivity.
- [Local Model Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-response-generators/response-generation-configurations/conversational-response-generation/local-model-generation.md) — Enables the generation of conversational responses using local large language model binaries to avoid external network calls. ([source](https://docs.vocode.dev/open-source/local-conversation.md))
- [Synthetic Speech Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/multimodal-processing-tools/synthetic-speech-generation.md) — Utilizes speech synthesis providers to generate natural-sounding synthetic voices from text input. ([source](https://github.com/vocodedev/vocode-core/blob/main/roadmap.md))
- [Voice Discovery Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/speech-processing/voice-synthesis/voice-discovery-interfaces.md) — Provides APIs and utilities to query and retrieve available voice identifiers and metadata from synthesis providers. ([source](https://docs.vocode.dev/api-reference/voices/get-voice.md))
- [Latency Adjustments](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-agent-capabilities/real-time-streaming/agent-response-streams/latency-adjustments.md) — Scales pauses before AI responses based on speed coefficients or user speaking rates. ([source](https://docs.vocode.dev/open-source/conversation-mechanics.md))
- [User Interruption Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/planning-interruption-callbacks/user-interruption-detection.md) — Detects and manages user interruptions to determine when the AI should stop speaking. ([source](https://docs.vocode.dev/open-source/conversation-mechanics.md))
- [Provider-Agnostic Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-agnostic-model-interfaces.md) — Provides abstraction layers that standardize inputs and outputs across multiple transcription, synthesis, and LLM providers.
- [Responsiveness Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-and-text-conversion/controllable-speech-conversations/responsiveness-tuning.md) — Adjusts speech endpoint detection and response speed to refine the natural flow of dialogue. ([source](https://docs.vocode.dev/conversational-dials.md))
- [Speech Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-synthesis.md) — Converts text to spoken audio using configurable voices across a wide range of supported locales. ([source](https://docs.vocode.dev/open-source/language-support.md))
- [Incremental Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-synthesis/incremental-synthesis.md) — Generates speech incrementally via WebSockets or gRPC to minimize latency in real-time conversations. ([source](https://docs.vocode.dev/open-source/using-synthesizers.md))
- [Unified Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-to-text-integrations/unified-model-interfaces.md) — Provides a unified interface for connecting voice agents to diverse speech-to-text, language, and text-to-speech models. ([source](https://docs.vocode.dev/open-source/python-quickstart))
- [Telephony-Integrated Autonomous Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/telephony-integrated-autonomous-agents.md) — Provides telephony capabilities as a tool for autonomous agents to make calls and act on outcomes. ([source](https://docs.vocode.dev/open-source/langchain-agent-dep.md))
- [Local Speech Synthesis](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech/local-speech-synthesis.md) — Provides the ability to run speech synthesis models locally for improved privacy and lower latency. ([source](https://docs.vocode.dev/open-source/local-conversation.md))
- [Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-assistants/tool-integrations.md) — Equips voice assistants with the ability to trigger external APIs, webhooks, and software actions.
- [Voice Cloning](https://awesome-repositories.com/f/artificial-intelligence-ml/voice-cloning.md) — Supports the creation of synthetic replicas of human voices for personalized AI interactions. ([source](https://docs.vocode.dev/voices.md))

### Networking & Communication

- [API-Driven Call Automation](https://awesome-repositories.com/f/networking-communication/telephony-services/telephony-session-managers/api-driven-call-automation.md) — Handles inbound and outbound telephony conversations using configurable agents initiated and managed via API. ([source](https://docs.vocode.dev/hosted-quickstart.md))
- [Call Lifecycle Management](https://awesome-repositories.com/f/networking-communication/call-lifecycle-management.md) — Provides comprehensive management of inbound and outbound call lifecycles, including start, termination, and metadata retrieval. ([source](https://docs.vocode.dev/api-reference/agents/create-agent.md))
- [AI-Powered Inbound Call Answerers](https://awesome-repositories.com/f/networking-communication/inbound-call-routers/ai-powered-inbound-call-answerers.md) — Provides an AI-powered system to answer incoming phone calls and interact with users using conversational agents. ([source](https://docs.vocode.dev/open-source/telephony))
- [Webhook-Based Call Acceptors](https://awesome-repositories.com/f/networking-communication/inbound-call-routers/webhook-based-call-acceptors.md) — Implements a webhook-based system to accept incoming phone calls and establish bidirectional media streams for AI processing. ([source](https://docs.vocode.dev/open-source/telephony.md))
- [Outbound Call Initiators](https://awesome-repositories.com/f/networking-communication/outbound-call-initiators.md) — Enables the programmatic initiation of outbound phone calls to specific numbers using defined prompts. ([source](https://docs.vocode.dev/open-source-quickstarts.md))
- [Real-Time Voice and Video Communication](https://awesome-repositories.com/f/networking-communication/real-time-voice-and-video-communication.md) — Provides comprehensive control over the voice call lifecycle, including starting, ending, and monitoring real-time status. ([source](https://docs.vocode.dev/api-reference/calls/create-call.md))
- [Real-Time Voice Backend Hosting](https://awesome-repositories.com/f/networking-communication/real-time-voice-backend-hosting.md) — Exposes websocket routes to handle real-time streaming voice interactions between clients and the server. ([source](https://docs.vocode.dev/open-source/react-quickstart.md))
- [Call Lifecycle Management](https://awesome-repositories.com/f/networking-communication/telephony-services/call-control-interfaces/call-lifecycle-management.md) — Manages the full lifecycle of voice conversations, including starting, terminating, and tracking active session status. ([source](https://docs.vocode.dev/api-reference/numbers/get-number.md))
- [Telephony Session Managers](https://awesome-repositories.com/f/networking-communication/telephony-services/telephony-session-managers.md) — Provides a specialized integration layer to attach conversational agents to phone lines, WebRTC, and virtual meetings.
- [Call Traffic Routing](https://awesome-repositories.com/f/networking-communication/telephony-services/telephony-session-managers/call-traffic-routing.md) — Maps phone numbers to specific AI agents to route incoming and outgoing telephony traffic. ([source](https://docs.vocode.dev/agents.md))
- [Answering Machine Detection](https://awesome-repositories.com/f/networking-communication/answering-machine-detection.md) — Determines if a call is answered by a voicemail system to decide whether the agent should continue or hang up. ([source](https://docs.vocode.dev/machine-detection.md))
- [Call Transferring](https://awesome-repositories.com/f/networking-communication/call-transferring.md) — Redirects current voice conversations to different phone numbers to perform hand-offs to other users. ([source](https://docs.vocode.dev/actions.md))
- [Multi-Channel Voice Deployment](https://awesome-repositories.com/f/networking-communication/multi-channel-voice-deployment.md) — Enables voice interactions over telephony, web, and meeting software across different communication channels. ([source](https://docs.vocode.dev/open-source/what-is-vocode.md))
- [Automated Outbound Dialers](https://awesome-repositories.com/f/networking-communication/outbound-call-initiators/automated-outbound-dialers.md) — Provides automated outbound dialing capabilities to start voice conversations triggered by scripts. ([source](https://docs.vocode.dev/open-source/telephony.md))
- [WebRTC Audio Streaming](https://awesome-repositories.com/f/networking-communication/real-time-audio-capture-protocols/webrtc-audio-streaming.md) — Connects agents to web applications using the WebRTC protocol for real-time audio interaction. ([source](https://docs.vocode.dev/open-source/livekit-webrtc.md))

### Graphics & Multimedia

- [Cross-Channel Audio Routing](https://awesome-repositories.com/f/graphics-multimedia/voice-channel-audio-delivery/cross-channel-audio-routing.md) — Streams voice data across telephony, WebRTC, and meeting platforms using a unified backend routing mechanism.
- [Cross-Platform Audio Routing](https://awesome-repositories.com/f/graphics-multimedia/audio-music/audio-streaming-engines/audio-playback-engines/cross-platform-audio-routing.md) — Streams voice data across telephony, web interfaces, and meeting platforms for cross-platform communication. ([source](https://docs.vocode.dev/welcome.md))
- [Speech Synthesis & TTS](https://awesome-repositories.com/f/graphics-multimedia/audio-music/speech-synthesis-tts.md) — Converts text into spoken audio and directs the output to available system speakers. ([source](https://docs.vocode.dev/open-source/playground.md))

### Web Development

- [Speech Synthesis Providers](https://awesome-repositories.com/f/web-development/third-party-integrations/speech-synthesis-providers.md) — Integrates modular plugins for connecting external text-to-speech services to customize agent voice characteristics. ([source](https://docs.vocode.dev/open-source/how-it-works.md))
- [Voice-Enabled Web Interfaces](https://awesome-repositories.com/f/web-development/voice-enabled-web-interfaces.md) — Creates web-based applications that allow users to interact with AI via spoken conversation. ([source](https://docs.vocode.dev/open-source-quickstarts.md))

### Business & Productivity Software

- [Telephony Routing](https://awesome-repositories.com/f/business-productivity-software/business-communication-suites/telephony-routing.md) — Routes voice calls through centralized telephony infrastructure to enable phone-based conversations. ([source](https://github.com/vocodedev/vocode-core/blob/main/roadmap.md))
- [Multi-Platform Meeting Services](https://awesome-repositories.com/f/business-productivity-software/multi-platform-meeting-services.md) — Integrates AI agents with multiple virtual meeting platforms to interact with live participants. ([source](https://cdn.jsdelivr.net/gh/vocodedev/vocode-core@main/README.md))
- [AI Meeting Participants](https://awesome-repositories.com/f/business-productivity-software/multi-platform-meeting-services/ai-meeting-participants.md) — Integrates AI agents into virtual meeting platforms via dial-in to facilitate real-time conversations. ([source](https://github.com/vocodedev/vocode-core/blob/main/roadmap.md))

### Development Tools & Productivity

- [Agent Tooling and Event Configurations](https://awesome-repositories.com/f/development-tools-productivity/event-automation-hooks/agent-tooling-and-event-configurations.md) — Equips agents with specific actions and configures webhooks to notify external systems of conversation events. ([source](https://docs.vocode.dev/agents.md))
- [Conversation Event Webhooks](https://awesome-repositories.com/f/development-tools-productivity/event-triggers/github-event-integrations/webhook-event-receivers/conversation-event-webhooks.md) — Triggers external HTTP webhooks based on conversation lifecycle events such as call endings or machine detection.

### Testing & Quality Assurance

- [Programmatic Termination Logic](https://awesome-repositories.com/f/testing-quality-assurance/llm-as-a-judge-scoring/simulation-termination-logic/programmatic-termination-logic.md) — Implements programmatic logic to terminate active conversations based on user phrases or internal agent state. ([source](https://docs.vocode.dev/actions.md))