Libraries & frameworks
moonshine
moonshine-ai/moonshine
An open-source voice toolkit for developers building real-time voice agents, with fast on-device speech-to-text and text-to-speech libraries across Python, mobile, web, and edge devices.
Topics
Related projects
yovoice2.1kA local-first desktop studio for speech, voice cloning, singing, and music production, running text-to-speech and generative audio models entirely on the user's machine without cloud fees.
skills556A collection of Agent Skills that teach coding assistants to build with ElevenLabs: text-to-speech, speech-to-text, music, sound effects, dubbing and voice agents.
vosk-api15.2kAn offline speech recognition toolkit with small models and bindings for many languages, built for apps and devices.
aeneas2.9kA Python/C library and command-line toolkit for forced alignment. It synchronizes audio with text and exports timing maps for subtitles, EPUB, research, and captions.
gTTS2.6kgTTS is a Python library and CLI that turns text into spoken mp3 using Google Translate's text-to-speech endpoint, with sentence tokenization and customizable text pre-processors.
Android-MVVM-Architecture-Android-Voice-AI-SDK2.6kA reusable Android SDK that adds a full voice-to-Claude-to-speech conversation pipeline to any app.