commit 51cfb61f0113aed6ee350e2635f468de09930dd7 equwal <truex@equwal.com> 2026-09-22 17:34:53 -0700 Name DeepInfra as the speech service of cloud captions subread.space now sends cloud captions to DeepInfra, not Groq (equwal/subplz-web#11). The privacy line on the screen and the README say so, and link to the data privacy page of DeepInfra.
README.md | 7 ++++--- app/src/main/res/values/strings.xml | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/README.md b/README.md index c781475..ce747b9 100644 --- a/README.md +++ b/README.md @@ -36,7 +36,7 @@ and the old one stops. ## Cloud captions -The cloud uses Whisper large-v3 turbo on Groq, through subread.space. It is +The cloud uses Whisper large-v3 turbo on DeepInfra, through subread.space. It is more exact than the models that a phone can run, and it uses less battery. | Pack | Price | @@ -54,8 +54,9 @@ account: write to the contact address on subread.space with the old id and the receipt, and we move the hours. What goes where: each piece of speech goes to subread.space, which gives it -to Groq for the text. Neither keeps the sound or the text. The app sends -nothing while the phone makes the captions. +to DeepInfra for the text. subread.space keeps neither the sound nor the +text. DeepInfra says that it does not store them ([data privacy](https://docs.deepinfra.com/account/data-privacy)). +The app sends nothing while the phone makes the captions. ## What the phone cannot capture diff --git a/app/src/main/res/values/strings.xml b/app/src/main/res/values/strings.xml index e123b41..655da0c 100644 --- a/app/src/main/res/values/strings.xml +++ b/app/src/main/res/values/strings.xml @@ -6,7 +6,7 @@ <string name="step_where">1. Where the captions are made</string> <string name="where_phone">On this phone: free, and no sound leaves the phone</string> <string name="where_cloud">In the cloud: a larger model, better captions, less battery. It costs hours.</string> - <string name="cloud_privacy">In the cloud, each piece of sound goes to subread.space and to Groq, which make the text. Neither keeps the sound or the text.</string> + <string name="cloud_privacy">In the cloud, each piece of sound goes to subread.space and to DeepInfra, which make the text. subread.space keeps neither the sound nor the text, and DeepInfra says that it does not store them.</string> <string name="cloud_left">Cloud hours left: %1$s. Account: %2$s</string> <string name="cloud_offline">Cloud hours: no connection to subread.space.</string> <string name="cloud_closed">Cloud captions are not open yet on subread.space.</string>