What kind of TTS are you looking for? Whisper I believe is the standard. It should be able to run on modest hardware. https://github.com/openai/whisper

private whisper from ppq (you can use completely local models too)

Depends on complexity and how you implement it - Claude suggested a few open router options to me, mistrel and openAI TTS is lagging behind

Depends how much flatness you can tolerate: Piper (local, MIT-licensed, zero API cost — just CPU) is the free option, but the built-in voices read pretty flat/toneless. We started there for a podcast series and moved to Google's Gemini TTS API once that got in the way — usage-based per call, not...

LocalAI the install some vits piper models

tts is just synthesis. it's not really ai. i know claude has one but it's practically free, there is all these settings for different kinds of voices. here's a good starting point: For a cheap, high-quality, and human-like TTS system, the main decision is between an open-source model you run locall...

Late to this, and Piper's already been covered, so let me push on the framing instead: you said at the end it's for reading articles and PDFs on the go. That changes the answer. Everything suggested here is a TTS engine — something you'd wire up, feed text to, and get audio back. But "on the go, ...