Filmora
Filmora - AI Video Editor
Edit Faster, Smarter and Easier!
OPEN

STT and TTS in Filmora for Windows

Filmora provides Speech-to-Text (STT) and Text-to-Speech (TTS) tools for working with spoken and written content during video editing. STT automatically converts spoken dialogue into on-screen subtitles, while TTS transforms written text into voiceovers with AI-powered voices. With Smart Text Correction, Filmora can also detect problematic subtitle text and provide correction suggestions during the transcription workflow.

Upgrade to the Newest Filmora Unleash Your Freedom to Creativity
Free Download
For Win 7 or later (64-bit)
Free Download
For macOS 10.15 or later

Using Speech to Text

Turn on the correction option before generating your captions by following these steps:

Step 1. Begin With a New Filmora Project

Launch Filmora and create a new project. Import the video into the interface, then drag it onto the editing Timeline to prepare it for transcription.

import video into filmora timeline

Step 2. Access the Speech to Text Feature

Once the video is within the interface, right-click on it to expand a list of options. Now, locate the Speech to Text option from there.

open speech to text feature

Step 3. Configure Settings, Generate Text

Next, choose the Language for the text using the drop-down menu and choose whether you want a translation or not. Select the format for the output as SRT and hit the Generate button.

configure speech to text settings

Step 4. Enable Smart Text Correction

In the Speech to Text settings, turn on Smart Text Correction. This allows you to automatically highlight potentially incorrect subtitle sections and receive intelligent modification suggestions before generating the captions.

enable the smart correction

Step 5. Preview Text and Export

Once the text across speech is generated, drag it to the timeline to add it to the video. Preview the results in the corresponding window and save them to the device using the Export button.

preview subtitles and export video

Other Ways to Access Speech to Text

Filmora provides additional entry points for Speech to Text, allowing you to start transcription from the homepage, Tools menu, or timeline toolbar.

From Homepage

After launching Filmora on your device, head to the Toolbox on the left. Now, locate the AI Captions feature and click on it.

access ai captions from toolbox

From Tools Menu

Go to the top menu bar, click Titles, and select AI Captions. Then select Speech to Text to start the conversion.

open Speech to Text menu

From Timeline Toolbar

Import your video and place it on the timeline. Expand the toolbar above it and select the Speech to Text feature to access transcription directly from the editing workspace.

access speech to text toolbar

Using Text to Speech

Filmora's Text-to-Speech feature converts written content into AI-generated narration. You can select from the available voices or use Voice Modeling to create a voice based on your own, making it easier to add spoken narration without recording each line manually.

Step 1. Enter Text and Select a Voice

Open Text to Speech, enter or paste your script into the text box, and select the required language. Choose a voice from the Voice Library or Modeling Voice options. You can also use options such as Auto Split, AI Polish, or AI Expand Text when needed. Click Generate to create the voiceover.

configure text to speech voice

Step 2. Preview and Export the Result

After Filmora generates the speech, review the resulting content on the timeline and preview it to check the output. Make any required adjustments, then click Export in the upper-right corner to save the finished video.

preview and export generated speech