Run This Ai
EN DE

Moonshine Voice

Real-time on-device voice AI: speech-to-text, intent recognition and text-to-speech for building fast, private voice agents and interfaces.

★ 10,764 GitHub MIT voicesttttsspeech-to-texttext-to-speechvoice-agentson-devicereal-timeintent-recognitiontranscription Speech & Audio

Overview

Moonshine Voice is an open-source AI toolkit for developers building real-time voice agents and applications. Everything runs on-device, so it is fast, private, and needs no account, credit card, or API keys. Its models are optimized for live streaming, offering low-latency responses by doing much of the work while the user is still talking, with higher accuracy than Whisper Large V3 at the top end and tiny 1MB models for constrained deployments. The same library runs on Python, iOS, Android, macOS, Linux, Windows, Raspberry Pi, IoT devices, microcontrollers, DSPs and wearables. High-level APIs cover transcription, text-to-speech, voice cloning, speaker diarization, command recognition and conversational agents, with support for many languages.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  moonshine:
    image: spectralmemories/moonshine
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/moonshine:/data

Best VPS for Moonshine Voice →

Related tools

ebook2audiobook

Generate audiobooks from e-books with voice cloning and 1158+ languages.

FunASR

End-to-end speech recognition toolkit with streaming ASR, VAD, punctuation, and speaker diarization

DIA

Ultra-realistic dialogue TTS in one pass

NeMo Speech

NVIDIA scalable generative AI framework for speech — ASR, TTS, and speech language models in one toolkit.

Supertonic

Lightning-fast, on-device, multilingual TTS running natively via ONNX.

Piper

Fast, local neural text-to-speech that runs fully offline

Guides & articles

How to Build a Voice Agent with Moonshine Voice: Step-by-Step Tutorial

From pip install to a spoken conversational agent: a hands-on tutorial for building real-time, privacy-first voice apps with Moonshine Voice.

Aug 11, 2026

Moonshine Voice: A Complete Guide to On-Device Real-Time Voice AI

Moonshine Voice brings fast, private, on-device speech-to-text, intent recognition, and text-to-speech to any platform — with accuracy that rivals Whisper Large V3.

Aug 11, 2026