Give agents a voice

Voice +1

Fish Audio

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

Coding +1

VoiceStudio

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

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

Voicebox

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

Inference +1

Pocket TTS

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

Voice +2

MLX-Audio

Voice +1

OpenLive

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) r

Voice +1

MiniMax-MCP

Official MCP server exposing MiniMax text-to-speech, voice cloning, image and video generation APIs to MCP clients.

Voice +1

Chatterbox

Open zero-shot voice-cloning TTS family with multilingual, low-latency Turbo, and CPU-scale Nano variants

Voice +1

Neuphonic

Text-to-speech via Neuphonic's API.

Deepdub

Text-to-speech via Deepdub AI's streaming WebSocket API.

ElevenLabs

Expressive text-to-speech with word-level timing plus file-based transcription.

Gradium

Low-latency streaming speech-to-text and text-to-speech via Gradium.

LMNT

Text-to-speech via LMNT's streaming API.

Murf AI

Text-to-speech via Murf AI's streaming WebSocket API.

Pinch

Real-time speech-to-speech translation for voice agents.

Respeecher

Real-time text-to-speech via Respeecher's streaming WebSocket API.

Soniox

Real-time WebSocket speech-to-text and streaming text-to-speech.

Typecast

Text-to-speech using Typecast's neural voices.