They always appreciate it when apps try to be more inclusive by adding things like captions and transcripts because they make it so much easier to follow along with everything from Netflix shows to Meet calls. With the Pixel 7’s arrival, voice transcripts were added to Google Messages, while transcriptions were added to Telegram’s paid Premium tier. It appears that WhatsApp will soon join the fray with its own voice message transcription system.
In 2021, WhatsApp’s work on transcriptions was first mentioned to us. The feature, as it was described at the time, relied on the built-in iPhone tool for converting audio files to text. Today, some evidence appears in the most recent beta, indicating that transcription is finally coming soon to WhatsApp.
WABetaInfo discovered a dialogue box in the iOS beta of WhatsApp that explains the reasons why the app might not be able to transcribe a voice note received in a chat. The tool might not be able to pick up any words in the audio, or the language might be different from what is set as the default. Additionally, it lets you change the language, indicating that it supports multiple languages from the start.
They don’t yet know how well the feature works for iOS users in its current beta state, if at all. However, the report makes it clear that WhatsApp is still making use of the iPhone’s on-device transcription capabilities to completely offline voice notes into text, just like in the previous tests. This method is great for your privacy, but in order for the feature to work, you will need to download the right language packs to your phone.
The WhatsApp beta version 23.3.0.73 is available to iPhone users who are members of Apple’s TestFlight beta testing program. Otherwise, you’ll have to wait for the stable release to include the transcription feature.
Naturally, our primary concern is what this development might mean for Android transcription, but they are still waiting for information. WhatsApp could use Google’s excellent tool, which has proven to be extremely reliable in apps like Google Recorder and Meet, if it does not have its own voice-to-text conversion engine.