| Metric | v2.1.5 (Premiere 2024) | v2.1.6 (Premiere 2025) | | :--- | :--- | :--- | | | 4 min 20 sec | 3 min 55 sec | | RAM usage after 2 hours | 14.2 GB | 6.8 GB | | Export time (text panel burned in) | 12 min 10 sec | 11 min 02 sec |
As video content consumption shifts heavily toward social media platforms requiring burnt-in captions, this update addresses the editor's need for speed without compromising precision. adobe speech to text v216 for premiere pro 2025 upd
Here is everything you need to know about the v2.1.6 update. | Metric | v2
The v2.1.6 update focuses on accuracy and deep integration with , a feature that allows you to edit your video by simply cutting and rearranging the generated transcript. One complaint about earlier builds was the over-generation
One complaint about earlier builds was the over-generation of captions for sighs, ums, and heavy breathing. v2.16 introduces an adjustable . You can now set a decibel threshold (from -24dB to -12dB) below which the engine will ignore sounds. This cleans up the transcript dramatically without needing to manually delete the "ahhs" and "mmhmms."
Based in the Adobe Video Community, this review is part of our ongoing "Post-Lab" series analyzing AI tools in non-linear editing.