Post B2pOjLip46d21mMbLc by GrapheneOS@grapheneos.social
 (DIR) More posts by GrapheneOS@grapheneos.social
 (DIR) Post #B2n3LeEW6R5f8T7pvE by GrapheneOS@grapheneos.social
       2026-01-29T21:54:34Z
       
       1 likes, 2 repeats
       
       We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.
       
 (DIR) Post #B2pOjLip46d21mMbLc by GrapheneOS@grapheneos.social
       2026-01-29T22:04:57Z
       
       0 likes, 0 repeats
       
       We're going to build our own speech-to-text implementation to go along with this too. We're starting with an English model for both but we can add other languages which have high quality training data available. English and Mandarin have by far the most training data available.
       
 (DIR) Post #B2pOjMpawPdjT4XWXg by GrapheneOS@grapheneos.social
       2026-01-29T22:06:37Z
       
       0 likes, 0 repeats
       
       Existing implementations of text-to-speech and speech-to-text didn't meet our functionality or usability requirements. We want at least very high quality, low latency and robust implementations of both for English included in the OS. It will help make GrapheneOS more accessible.
       
 (DIR) Post #B2pOjNV4SCohXhweBs by GrapheneOS@grapheneos.social
       2026-01-29T22:11:00Z
       
       0 likes, 0 repeats
       
       Our full time developer working on this already built their own Transcribro app for on-device speech-to-text available in the Accrescent app store. For GrapheneOS itself, we want actual open source implementations of these features rather than OpenAI's phony open source though.
       
 (DIR) Post #B2pOjO8Q5uIBVkM4WW by GrapheneOS@grapheneos.social
       2026-01-29T22:18:39Z
       
       0 likes, 0 repeats
       
       Whisper is actually closed source. Open weights is another way of saying permissively licensed closed source. Our implementation of both text-to-speech and speech-to-text will be actual open source which means people can actually fork it and add/change/remove training data, etc.
       
 (DIR) Post #B2pOjOm7iI3FUsvmPQ by Bernard@friends.ravergram.club
       2026-01-29T22:21:34Z
       
       0 likes, 0 repeats
       
       @GrapheneOS This is a great addition. I have been using Sherpa TTS  https://github.com/woheller69/ttsengine and Futo Keyboard for STT. https://keyboard.futo.org/
       
 (DIR) Post #B2pOjPm9zdfubHxK6a by tuxicoman@social.jesuislibre.net
       2026-01-31T01:04:23Z
       
       0 likes, 0 repeats
       
       @Bernard @GrapheneOS I have the same setup.But my friend complain Futo is not good enough in vocabulary (french) and is hit and miss sometimes then.I feel most of the voice recognition is based on probability and therefore context plays a big role maybe.