huggingface/speech-to-speech
Build local voice agents with open-source models
This project helps you build conversational AI agents that understand spoken language and respond naturally. It takes live speech input, processes it, and generates spoken responses, making it ideal for creating interactive voice assistants. The intended users are developers looking to implement custom voice agent solutions locally or via server/client setups.
4,541 stars. Actively maintained with 21 commits in the last 30 days.
Use this if you need to build a custom, real-time voice agent using open-source speech-to-text, language models, and text-to-speech components, especially for local deployment or specific hardware like Apple Silicon.
Not ideal if you're looking for a pre-built, off-the-shelf voice assistant solution that requires no programming or integration work.
Stars
4,541
Forks
518
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
21
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/huggingface/speech-to-speech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
alphacep/vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
linto-ai/WebVoiceSDK
Buildings block for voice-enabled applications in the browser
Picovoice/speech-to-text-benchmark
speech to text benchmark framework
vox-serve/vox-serve
A Streaming-Native Serving Engine for TTS/STS Models
Lex-au/Orpheus-FastAPI
High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and...