Text to speech panel

The Text to speech panel creates voiceover audio from typed text. Use it for narration, placeholder reads, tutorials, product demos, and social-video scripts.

Open Text to speech

1. Open a project.
2. In the left asset panel, click Text to speech.
3. The TTS panel opens with a text input and voice controls.

Generate a voiceover

1. Type or paste your script.
2. Choose a voice.
3. Set the speed.
4. Click Generate.
5. Wait for the MP3 to be created.
6. Preview the generated speech.
7. Add it to the project or timeline.

Keep scripts short enough to review quickly. The input limit is 4096 characters.

Voice selection

The visible voices come from the editor app's configured TTS voice list.

When choosing a voice, consider:

• Tone: calm, energetic, professional, playful.
• Audience: tutorial, ad, product demo, entertainment.
• Pace: whether the default speed sounds natural.
• Fit: whether the voice matches the visual style.

Generate a short test before committing to a long voiceover.

Speed control

Speed can range from 0.5x to 2x.

Guidelines:

If captions will be added, do not make speech too fast to read.

Preview generated speech

Always preview before adding to the timeline.

Listen for:

• Mispronounced names.
• Awkward pauses.
• Wrong tone.
• Too fast or too slow delivery.
• Script errors.

If something sounds wrong, edit the text and regenerate.

Add generated speech to the timeline

1. After generation, click Add to project or Add to timeline.
2. The generated MP3 becomes a project audio asset.
3. Drag it to an audio track if it is not placed automatically.
4. Trim it to the right start time.
5. Add fades if needed.
6. Mix it with music and original audio.

Write scripts that sound natural

TTS sounds better when text is written for speech.

Tips:

• Use short sentences.
• Add punctuation where you want pauses.
• Spell unusual names phonetically if needed.
• Avoid long paragraphs.
• Read the script out loud before generating.

Add captions after TTS

After adding TTS voiceover:

1. Put the TTS audio on the timeline.
2. Open Captions.
3. Generate captions from the timeline audio.
4. Review timing and words.
5. Style captions in the Text properties.

Configuration requirements

Text to speech requires one of these to be configured in the editor app:

• OpenAI API key.
• Azure OpenAI TTS credentials.

If TTS is unavailable, the panel may show a configuration message.

Troubleshooting

See also

• Audio editing and effects
• Captions and subtitles
• Left asset panel