M
Mastra•2w ago
Sujay

What is the better approach for STT and TTS at Mastra level with Voice on mobile?

We have a React Native CLI (without Expo) app, where we are sending every 5-10s of audio chunks after the user clicked on the Voice mode button on the mobile app. We are not going for STS (speech-to-speech) Do we go for implementing Web Socket and connecting it to Mastra (backend) or do we have to go with node stream only method? Don't you think each chunk will have HTTP overhead?
6 Replies
Mastra Triager
Mastra Triager•2w ago
šŸ“ Created GitHub issue: https://github.com/mastra-ai/mastra/issues/10675 šŸ” If you're experiencing an error, please provide a minimal reproducible example whenever possible to help us resolve it quickly. šŸ™ Thank you for helping us improve Mastra!
Sujay
SujayOP•7d ago
Any update?
Abhi Aiyer
Abhi Aiyer•7d ago
I would use WebSockets, you have a single persistent connection and lower latency if youre using HTTP2 it could actually work without websockets You could probably start with HTTP though and see
Sujay
SujayOP•7d ago
You are great šŸ’Æ, I was fumbling and bumbling and you just showed up and you made me stumbled on the perfect path šŸ›£ļø Thank you so much Abhi šŸ™šŸ˜€
Abhi Aiyer
Abhi Aiyer•7d ago
Of course Sujay! anytime In a few releases we will be doing Server Adapters which allows you to attach mastra server to your own server instance This is gonna allow you to control so much more especially if you wanna do websocket transport!!
Sujay
SujayOP•7d ago
Ohho, eagerly waiting for those ✨ Thank you Abhi and Team Mastra. Mastra is my love.

Did you find this page helpful?