We also have better models in training.
Also the underlying system would get faster, the models smaller over time along with grammar correction, in voice commands and better live preview models
They have development costs to pay for which is substantial. Not sure why you are framing it as greedy and complaining it should be free vs celebrating someone putting this out there.
Thanks.
I don't want my data, especially voice and text to be sent to servers.
That's why I built this.
I love my competitor's product, but the amount of private data I sent over was really uncomfortable to me.
Especially when sometimes it included Phone Numbers and some private info.
At the same time, tools like mine will fall behind if I don't keep updating the models.
If you care so much about user privacy, why do you exfiltrate events named "dictation_started", "dictation_completed", "dictation_rejected", "dictation_blocked", "insertion_failed", etc to PostHog, with properties named: "audio_seconds", "latency_ms", "duration_ms", "install_id", etc?
Because anyone building a system needs performance metrics to understand how it’s behaving in aggregate / if they update the model? With the exception of install_id these all seem innocuous. Install_id is maybe needed anyway for purchase management. Probably could use a session uuid to track the other metrics at the cost of blinding you to being able to find individual customers with a bad experience which is probably much more important for a small player like this.
Yes These metrics are there to check system issues.
Like Crashes and etc.
Also I need to check Model performance too.
However your data is yours, and this data will be anonymized too.
I really want Jexxa to be private and secure, as I am a heavy user of it too.
Both bundles contain quantized versions of the CohereLabs/cohere-transcribe-03-2026 model. The model in JEXXA.dmg is MLX int8 g64 affine quantized. JEXXA-Small.dmg has the same model but MLX int4 g32 affine quantized. There's also an int8 quantized WeSpeaker ECAPA-TDNN speaker-verification ONNX encoder. No acknowledgments for both models (doesn't the Apache 2.0 license require it? WeSpeaker's cc-by-4.0 license certainly does). Both bundles also contain full-blown Python 3.12.8 runtimes with about a dozen packages installed.
Apps are unsandboxed menubar apps and also contain PostHog analytics and Supabase auth. So, I wouldn't run it on any of my machines.
A few engineering hygiene issues like a .pytest_cache directory, Python code, .DS_Store files, etc.
Given the above, I suspect the "I am training better models." is just marketing speak.
14 comments
[ 0.25 ms ] story [ 12.1 ms ] threadAnother example of meaningless monthly payments for the right to use a static file on your own computer. It's burning your own CPU cycles too.
What a joke.
I love my competitor's product, but the amount of private data I sent over was really uncomfortable to me. Especially when sometimes it included Phone Numbers and some private info.
At the same time, tools like mine will fall behind if I don't keep updating the models.
https://developer.apple.com/documentation/metrickit
> "Runs on your Mac — no upload, no queue"
> $8/month
Vibe-coded website.
Both bundles contain quantized versions of the CohereLabs/cohere-transcribe-03-2026 model. The model in JEXXA.dmg is MLX int8 g64 affine quantized. JEXXA-Small.dmg has the same model but MLX int4 g32 affine quantized. There's also an int8 quantized WeSpeaker ECAPA-TDNN speaker-verification ONNX encoder. No acknowledgments for both models (doesn't the Apache 2.0 license require it? WeSpeaker's cc-by-4.0 license certainly does). Both bundles also contain full-blown Python 3.12.8 runtimes with about a dozen packages installed.
Apps are unsandboxed menubar apps and also contain PostHog analytics and Supabase auth. So, I wouldn't run it on any of my machines.
A few engineering hygiene issues like a .pytest_cache directory, Python code, .DS_Store files, etc.
Given the above, I suspect the "I am training better models." is just marketing speak.
nb: The demo link without LinkedIn tracking slop: https://www.linkedin.com/posts/sankyde_jexxa-demo-httpsjexxa...
This is the model in question for newer versions.