Trying to translate video audio if that matters. Tried Deepl on my phone held up to the speaker but it doesn’t register for some reason.
I’d like this too, but I’m not sure it one app to do this exists. You can use vosk for dictation in multiple languages, various different open source text translation tools, and then use espeak to narrate in multiple languages. I don’t know if anyone’s put them together like that yet though.
But I think espeak doesn’t sound that great. There is probably better open source TTS now.
rhasspy’s Piper tts is a good engine and has some good models for English and Spanish. Integrated into some apps but isn’t difficult to code into an app.
Hows Piper stack up to something like Coqui, Tortoise, orBark?
Its very light to run even on just CPU (faster than realtime) and has decent quality. Good enough I made a personal project to turn books into audio books. But quality isn’t its main selling point. I think its better than googles tts but that isn’t saying much.