Soniox v5 Real-Time is now available.
Live speech AI is not batch transcription with lower latency. It has to turn raw, noisy, continuous audio into structured intelligence while people speak.
What’s new:
• Higher accuracy across 60+ languages
• Completely reengineered speaker separation
• Better spoken language identification
• Higher-quality real-time translation across 3,600+ language pairs
• Faster semantic endpointing for voice agents
• Better alphanumeric recognition
• More robust native context handling
Built for voice agents, meetings, captions, translation, dictation, customer support, contact centers, and multilingual products.
Read more:
https://t.co/z01GyIOvPh
Hey @superset_sh! Would be nice if the branch name could be auto-generated based on the initial prompt if I do not enter one when creating the workspace.
@zarifpr@conductor_build@superset_sh Having the layer between me and Claude Code did not sit right. Often got into a state where it would just hang while doing reviews etc. But might circle back and check it out again later.
@avimakesrobots@conductor_build@superset_sh Yeah. Do not care too much about the animations, but the ability to dock and re-arrange would be great.
I would also love to be able to bind cmd+1/cmd+2 to jump to given terminal windows (mainly because of terminal muscle memory). Now I just end up switching workspaces 😄
Mobile update time!
Capturing notes on mobile took too many steps. Open app, pick mode, pick type, pick tag, pick destination...
We just made it one tap. 👆
Widgets for Tana mobile are here. 🧵
Announcing Tana offline 🔌🎉
(just in time to go off-grid this weekend!)
We're super excited to launch our most-requested feature, offline mode! Not “select which pages to download” offline. Full knowledge graph offline.
Whether you are AWS's US-EAST-1 server or a knowledge worker reliant on Aussie broadband, sometimes you just need to disconnect 🔌
🧵 So here’s the quick what’s-what on working offline:
@UnforcedAG@AravSrinivas@tana_inc@AarashHeydari Check the config option to disable proxy, which should help for debugging. As for the parsing, it's easiest to use LLMs for that currently. We have a great Slack community with a ton of people building cool stuff, check out the channel called tana-ai-for-builders 🚀
@UnforcedAG@AravSrinivas@tana_inc@AarashHeydari Hey Aaron! Payload looks correct! Try setting "API Method" to "POST", and "Headers" to "content-type: application/json". I got it running on my end doing that.
This command node is very generic, so it requires some config 😅