Convert speech to text metadata

Adobe Premiere Pro and Soundbooth let you convert spoken words into text transcripts, which you edit and search just like other metadata properties. This powerful technology lets you navigate to time locations at which specific words are spoken, helping you better align edits, advertising, and subtitles.

The speech analysis feature can use any of several language-specific and dialect-specific libraries, such as libraries for Spanish and UK English.

Note: Accurate speech transcripts require good audio quality. Background noise significantly reduces accuracy. To remove such noise, use the tools and processes in Soundbooth.

Dan Ebberts provides a tutorial on the Adobe website that demonstrates the use of XMP metadata features. The tutorial shows how to convert speech to text metadata and create a simple video player with which you can navigate to the places where words are spoken. Adobe provides another white paper and demonstration on the Adobe website that shows an alternative method involving Soundbooth to accomplish a similar result.

For a video about searching speech to speed up editing, see the Adobe website.

Transcribe spoken words

  1. In the workspace, select a file or clip.

  2. At the bottom of the Metadata panel, click Transcribe.

  3. Set the Language and Quality options, and select Identify Speakers if you want to create separate transcripts for each person.

  4. Click OK.

    The spoken words appear in the Speech Transcript section. Processing time roughly equals clip length. If a clip is one minute long, for example, the transcript will appear after roughly one minute.

  5. (Required) Save the project to retain the transcript.

If you import files with a speech transcript into After Effects, each word appears as a layer marker in compositions.

Navigate to a specific word in a transcript

  1. In the Speech Transcript section, select the word.

    Timecode In and Duration indicate the precise location and length of your selection.

  2. To hear the selection, click either Play or Loop Playback. (The latter option repeatedly plays the selected word, with some preroll and postroll.)

Edit a transcript

 In the Speech Transcript section, do any of the following:
  • To correct a word, click it, and type.

  • To insert, delete, merge, cut, or copy words, right-click an existing word, and choose a command from the context menu.

Copy a complete transcript to the clipboard

You can copy a complete transcript to the clipboard for use in text-editing applications.

 Right-click the transcript, and choose Copy All.

Note: Because transcripts are associated with specific timecode, you cannot paste an edited transcript from another application into the Metadata panel.