For the past few days, we have been working on an open-source, self-hosted real-time speech-to-speech translation tool called PolyTalk.
The goal was that there are people and organisations who need privacy around the tool they are using, and for the speech-to-speech translation, we haven't had many options.
We built the tool with Ollama, Faster Whisper, and Piper.
The tool is not limited to speech-to-speech translation only, but you can also share any of your tabs, whether you're watching a YouTube video in another language, the tool will give you audio output in your target language.
We are aware of how often context and tone get lost in translation, so we ensured translation quality by processing complete sentences instead of individual words.
Now we are focused on context support and tone adaptation.
If this interests you, here is the GitHub repo: https://github.com/PolyTalkIO/polytalk