Give agents a voice

Voice

whisper.cpp

C/C++ port of OpenAI's Whisper speech-recognition model, dependency-free and optimized for on-device inference

Voice +2

NeMo

NVIDIA framework for building speech AI models, including ASR, TTS, translation, and speaker diarization

Voice

Asterisk

Open-source PBX; frame serializer to connect agent pipelines to an Asterisk WebSocket channel.

Voice +1

LiveKit

WebRTC transport and infrastructure for real-time audio/video agents.

Inference +1

LocalAI

Self-hosted engine that runs LLM, vision, voice, image, and video models on any hardware behind OpenAI-compatible APIs

Coding +2

OpenAI Agents SDK

Python framework for multi-agent workflows with handoffs, guardrails, sessions, sandbox and voice agents, and built-in tracing

Voice

Pipecat

Python framework for real-time voice and multimodal conversational agents, with composable pipelines over WebSockets or WebRTC

Voice

LiveKit Agents

Framework for building realtime, server-side voice agents with pluggable STT, LLM, and TTS and WebRTC/telephony support

Generative media +1

OpenMAIC

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

Deployment +2

Foundry Local

Foundry Local is an end-to-end local AI solution for building applications that run entirely on the user's device.

Inference +2

MLX-Serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mo

Voice +1

Fish Audio

Real-time text-to-speech via Fish Audio's WebSocket API.

Voice

FluidVoice

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a t

Generative media +1

PPT Master

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the op

Coding +1

VoiceStudio

The Open-Source Elevenlabs alternative AI Voice Clone, Dub, Dictate, Transcribe, Audiobook creator and Voice workflow studio.

Generative media +1

ArcReel

Open-source AI video workspace that turns a novel into characters, storyboards, and video clips with cross-shot consistency

Voice +1

Voicebox

Local-first voice studio to clone voices, generate speech in 23 languages, dictate into any app, and give MCP agents a voice

Memory

Moss

Knowledge-retrieval service that injects semantic search results into an agent's LLM context.

Coding +2

Terax AI

Lightweight (7MB) Terminal-first AI-native dev workspace

Coding

Openai Agents Js

Voice +2

Jarvis

A 100% private AI voice assistant that lives on your computer (works offline). Talk naturally as if Jarvis is a third person in the room, an

Voice +2

Mlx Audio

Generative media +2

OGAM

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text,

Inference +1

Pocket TTS

A lightweight text-to-speech (TTS) application designed to run efficiently on CPUs.