Voice Transcription lets you speak while capturing a workflow, and Tango automatically turns what you say into clear step titles and descriptions.
Instead of editing steps and descriptions after capture, you can narrate what you’re doing as you go. Tango listens, then polishes your words into clear, concise step instructions automatically.
Voice Transcription is available to Tango Pro and Tango Enterprise users when creating How-To Guides.
The Voice Transcription is turned off by default and can be enabled when you start Capture.
How to capture using Voice Transcription
1. Open your Tango extension and click on "Start Capture"
2. If given the option between How-to guides and Automations, choose "How-to Guides".
If you did not see this option, proceed to the next step.
Voice Transcription is only supported by the How-to Guide format for now.
3. Click on the "Voice Transcription" icon in the lower right of your capture panel.
4. If this is your first time, you'll see a brief explanation of the feature first. Then, Click "Turn on Voice Transcription" to enable it.
5. For Chrome users: Click on "Allow while visiting the site" to enable. Note: Selecting any other option will not correctly enable voice.
For Edge: Click "Allow" to proceed.
6. Once Voice Transcription is enabled, you can begin speaking and continue recording your workflow.
An indictor in the bottom half of the capture panel shows that this feature is currently on.
7. If you'd like to see an active transcript of what you've said so far during capture, hover over the voice indicator and click "Show transcript".
8. When you are done recording your workflow, click the green checkmark at the bottom of the Capture panel.
9. Once finished, your workflow should include polished descriptions that reflect the context you gave while using Voice Transcription. All descriptions are editable should you need to change anything.
Note: Workflows with Voice Transcription enabled may take a few moments to load.
***
Created with Tango.ai
Privacy and control
You’re always in control of when voice is used.
Voice Transcription is off by default
Audio is not stored
There is no audio playback
Voice input is only used to generate step text