Request: Add Option To Use System Voice Recognition Provider

The Pebble app doesn’t currently give you the option to add alternative models, but most people already have models that work well for identifying speech built right into their phone via the phone’s voice dictation API, often through Google speech recognition services, or in my case, an open source alternative from FUTO.

It would be nice if users could simply set whatever default app/service is used for their system’s voice recognition as the system that the Pebble app would use for any voice transcription from the watch. Could also possibly fix the issue of local voice dictation not working when the phone is locked, given that service is often something used by voice assistants, which can (depending on the implementation) be available from the lock screen.

Yeah, I use FUTO and that would be awesome. I also plan to set up a dedicated speech to text server on my NAS/NextCloud server.

This is the main reason I got a Pebble watch - to set reminders and alarms with offline (or self-hosted), open source models. The only current offline option in the Pebble app (parakeet-tdt-0.6b-v3) is absolutely terrible at transcription and makes voice transcription as a feature on the watch unusable unless you choose to give your voice data to Whispr Flow.

FUTO has great voice transcription. I also tried using Wristotle but to use their offline models, it assumes your speech is being routed through Android’s default voice dictation API, which is not a setting in the Pebble app.