Speech to Text in Premiere Pro is an integrated workflow that allows you to automatically generate a transcript of your sequence and create customizable captions for your videos.
Speech to Text in Premiere Pro provides a comprehensive solution for transcribing and captioning videos. What used to be a cumbersome process is now automated and fully integrated within the video editing workflow, giving you full creative control to customize the results.
There is no additional cost. Speech to Text for Premiere Pro is included with your Creative Cloud all apps or Premiere Pro single app subscriptions.
With Premiere Pro 22.2 (and later) you can use Speech to Text offline. Premiere Pro includes an English language pack for transcriptions. Additional language packs can be downloaded individually. Once a language pack is installed, you can create transcriptions of your videos without an internet connection.
Speech to Text offers exceptional accuracy and Beta testers around the world have confirmed this in all currently supported languages. If there are errors, such as the spelling of names or words in other languages, these can be easily corrected in the Text panel .
Speech to Text offers the only integrated captions workflow within an NLE, including every step in the workflow, from generating transcriptions to captioning your video and the full range of captions export options.
Yes. Speech to Text leverages AI technology to generate transcripts and Adobe Sensei machine learning to position captions on the timeline so that they match the pacing and cadence of the spoken words.
Yes. Speech to Text has been developed with security in mind. User files are encrypted in transit and during the transcription process. As soon as a transcription is completed, the user files are deleted.
Speech to Text enables users to remain GDPR-compliant, as the transcription service is hosted on servers based in the European Union or the United States, depending on the user’s location.
Speech to Text is powered by a combination of Adobe proprietary technology — including Adobe Sensei machine learning— and 3rd-party technologies.
Speech to Text is available in Premiere Pro versions 15.4 and later as well as Premiere Pro (Beta). Open the Captions workspace to access the Speech to Text feature set.
Language packs are files you can download, allowing you to use Speech to Text without an internet connection. Premiere Pro 22.2 (and later) includes the English language pack. You can download other language packs individually, as needed. Languages packs are typically 650GB and offer the same accuracy as the original release of Speech to Text.
Speech to text is available for:
Language packs allow you to use Speech to Text without an internet connection. Transcriptions are up to 3 times faster than the original cloud-based transcription function in Speech to Text.
Yes. We're working on adding support for additional languages.
Yes. Whenever language packs are updated, these updates will be included automatically in future releases of Premiere Pro.
There is currently no set limit for fair and reasonable usage by individual subscribers, for their own projects.
Once you create a preset, a folder with the preset file is added to the Project Panel. If needed, you can export that file to share or store on your system.
After the transcript has been created, there is an option to display pauses as [...] in the transcript. Since the transcript text is editable, you can also add pauses manually.
Yes, you can add formatting, depending on the file type. Speech to Text supports SCC, MCC, XML, STL, SRT, and DFXMP sidecar formats, as well as some embedded caption formats for broadcast. For more information, see Supported file formats.