🗣️ How voice memos and auto-fill works with the new Tana Mobile iOS app

With the new Tana Mobile iOS app we are also introducing a more robust way to instantly transcribe voice memos.

Our goal is to help you capture ideas, tasks or fleeting thoughts on the go and turn these into structured Tana content with Supertags.
The details of this might change based on feedback and testing, we will post updates in the community Slack.

How does the new voice memo processing work?

Choose destination

The default destination from the Capture tab is now Today (but possible to change destination when capturing).
You can now navigate to any node in the Browse tab and capture into it.

Select Supertag and get fields auto-filled

You can now select a Supertag when you record the voice memo.
If you apply a Supertag, the fields will be shown in the voice recorder (so you know what to cover).
Auto-fill will attempt to fill in the fields based on the recording. The whole transcript will be shown below the fields.

Transcript refinement

The output will be a lightly formatted transcript (removing filler words).
For longer transcripts, AI will generate a title based on the content – If the voice memo is very short the title will be the transcript.

Source material

The audio file and raw transcript will always be available in source material that can be easily accessed from node options and a new audio icon next to the node.

Rewrite

The “Rewrite” feature you may have used on voice memos, will now create a temporary draft, that you can choose to move into the node or your notes if you are happy with it.
The intention is to allow you to experiment with Rewriting the content, but only keep what you are happy with.

Recording limit (temporary)

The new app has a temporary limit of 1 hr for voice recordings (we’re working to increase this!).
You will see a notification when closing in on the limit.

Sounds great! Do I need to do anything?

If you want to use the new setup as described above, you don’t need to do anything, just start capturing from the new app.

If you want to keep using the Inbox, you have two options (open link for instructions):

Q & A

How auto-fill works on voice memos

You can now select Destination, Supertag and output language when capturing voice memos

When a Supertag is selected, you will see the fields so you cover the ones you want to be auto-filled

If you want fields to be auto-filled, you should say the name of the field first, e.g. “Working on today – I need to buy a new TV for the office, and review feedback on the new app. General mood – Excited about the launch!”
The processing may try to fill in fields you haven’t addressed explicitly based on the content in the recording, if you would like to avoid this, see below.
If you want to specify how AI should treat a field, you can try adding in prompts in the AI instructions of the field in Field config:

Example for a field called “Working on today” on #standup Supertag

🚨 Known issue: Field auto-intialization is not working yet, so no fields in nodes created from mobile will be auto-intialized – but they may be auto-filled if you cover them in the recording.

How can I avoid some fields being auto-filled?

You can open the Supertag config > AI Section – copy a reference to the fields in “Fields to exclude”

How source material works

Our intention with this change has been to shorten the path from voice to value – allowing you to focus on the output, not the audio recording in itself. But we always want you to be able to go back to listen to the original recording if you need to, download it, play around with extracting things from it.
The source material is easily accessible with a new voice icon button on desktop and mobile, both from collapsed nodes and from the node options menu.

How Rewrite works

The Rewrite as function has existed for some time, but has gotten a slight revamp. Rewritten content will now be shown as a draft in a new panel, and will disappear unless you choose to keep it.
To keep it, you can drag it into the output node, move it to a location or add it to Today.
It is not possible to publish drafts, you will need to store it first.

Why is the new default destination Today, not Inbox?

When we asked our users, around half of them said they wanted to have captured content sent to Today, and many have set up workflows to move it over automatically.
Having content sent to an Inbox requires the user to manually process these, tag them and move them to the right location. With the possibility to choose destination and tag in the mobile app, we think more of this can happen in the moment of capture, rather than after, reducing the need for an Inbox.

Are voice memos only available for Tana Core subscribers?

Once the app is approved in App Store, all voice memos will be processed with AI, which requires a Tana Core subscription.
During the Testflight community beta period, all users will be able to test voice memos, without having a Tana Core subscription.

How many AI credits will be used for voice memo transcription?

15 min of voice memo transcription will require ca. 50 AI credits (5000 credits included per month in Tana Core subscription = 25 hours of voice memo transcription). In addition auto-filling will require some credits, how much depends on the content.
Using AI chat, the “Rewrite”, or other AI commands, on the source material after transcription, will require additional credits.

Will it no longer be possible to record audio and get the audio files into Tana as a free user?

No, this is no longer possible. Our focus is on turning voice into structured content in Tana, we will not be an ideal service for pure audio recordings.

Can I disable auto-fill on voice memos?

Not at the moment. If this is something that is important, we’d love to hear about it.

Can I continue to use the Inbox?

Yes, if you want to have content sent to the Inbox, this will still be possible.
1. In the current version, you need to pin the Inbox to make it appear in destination picker (Zoom into the Inbox, drag it to pinned).
2. You will need to select the Inbox as destination when capturing things in the mobile app.
We know this is not ideal, and will be looking into how we can make this easier for those who always want to capture to the Inbox.

If you want to keep using the Inbox, you have two options (open link for instructions):

Will voice memos sent to a regular node in my Tana be transcribed?

Yes, all voice memos will be transcribed with the new processing, regardless of which node they’re sent to.
The exceptions are the Inbox or nodes that have custom Audio commands set up. Scroll down to the section on technical details at the bottom.

I have set up my own command or have tweaked the standard Inbox Audio Processing Command on the Inbox – will this still work?

Yes, existing commands will continue to work as before, but be aware that these will require activity on the desktop client to run the processing, so the output will not be instantly available on mobile.

If you want to keep using the Inbox, you have two options (open link for instructions):

I’m confused, what is changing based on the current behavior?

Here’s a quick comparison between the old (Tana Capture) and new (Tana Mobile):

Comparison
Tana Capture (Old processing)
Tana Mobile (New processing)
Ability to choose location
No
Yes
Default location for captured voice memos
Inbox
Today
(this is the default; you can capture to any node in Tana with the new app)
Ability to add Supertag
No
Yes
Where does the transcription happen
Transcription requires activity on desktop client
Transcription happens instantly on server
When is the transcription available
Transcript not available until after you load the client to trigger the transcription command
Transcript available immediately, not necessitating client load
Output from voice capture on mobile
Audio file
Formatted transcript with field auto-fille (if tagged), and audio + raw transcript in Source material

In addition to the differences above, these are the new things you can do with voice memos in Tana mobile:

At time of recording a new voice memo, you can select a Supertag
If you apply a Supertag, we will show the fields in the voice recording, then attempt to auto-fill the fields based on the recording. Remaining content will be shown below the fields.
Transcription refinement
The output will be a lightly formatted transcript (removing filler words)
For longer transcripts, AI will generate a title based on the content – If the voice memo is very short the title will be the transcript
The raw audio file
The raw transcript and audio file will always be available in source material that can be easily accessed from node options and a new icon next to the node
The Rewrite feature
The “Rewrite” feature you may have used on voice memos, will now create a temporary draft, that you can choose to move into the node or your notes if you are happy with it.
Recording limit
The new app has a temporary limit of 1 hr for voice recordings (we’re working to increase this!). You will see a notification when closing in on the limit.

“Sounds great! Do I need to do anything?”

If you want to use the new setup as described above, you don’t need to do anything.

If you want to keep using the Inbox, you have two options (open link for instructions):

I have been getting multiple items tagged from one voice memo before, why is this not working now?

The old voice memo processing on Inbox was attempting to detect multiple items in one recording and would show these as tagged items in a tab. This is not yet supported in the new processing, but if you leave the Inbox unchanged, you will still get this behavior if you capture voice memos to the Inbox (see description above for how to capture to the Inbox).

I’m getting a different language for voice captures on desktop, how can I change this?

If you’re using Ctrl/Cmd+K > Capture Voice on desktop, you can do Ctrl/Cmd+K > Set transcription language (recommend selecting auto-detect if switching between languages)

If you’re using Live transcription, you can Shift+Click the button to switch language

Some technical details for advanced users:

Tip: If you want to make search nodes for content captured in the mobile app, you can use the search operator FROM MOBILE in the query editor.

Custom processing of audio recordings will still work as before.

🚨 The difference between keeping your old processing and the new, is that old processing will require activity on the desktop client to run, while the new processing will make transcript instantly available in the mobile app after recording.

We will check if the destination node selected has any “On child added” command looking for audio files set;

  • If they have, that command will process it on the desktop client (no processing will be done on server, you will get the audio file like before).
  • If you have modified the Inbox Audio Processing Conmmand (system command), this will work as before (but will require desktop activity to process).

  • If no custom commands on the Inbox, the recording will be processed with the new processing on server (and be instantly available in mobile app).

If you want to remove any old processing setup you have on the Inbox to get the new processing:

1. Go to the Inbox
2. Click the node options menu (three dots) in the header and select “Remove voice memo processing”

For advanced users: if you have multiple commands or custom commands set up on the Inbox;
Place the cursor on the Inbox title
Do Cmd+K > Configure node
Scroll down to the section “On child added”
Delete any commands you have here that is targeting voice memos/audio
Tana logo