Text-to-Speech

Glintia’s Text-to-Speech turns your written script into a natural-sounding voiceover. Choose from 592 AI voices in 82 languages, and when a character speaks the line, it lip-syncs to every word automatically. Text-to-Speech is included on every plan.

Available Voices

Standard

• 564 neural voices across 82 languages and 154 locales
• Regional variants listed separately, such as English (US) and English (UK)
• 47 voices with selectable speaking styles
• 2 AI credits per minute of audio, so Basic’s 400 monthly credits cover up to 200 minutes

Premium

• 28 multilingual ElevenLabs voices for especially lifelike, expressive reads
• Three models: v3 (expressive), Multilingual v2 and Turbo v2.5
• 0.5 AI credits per second of audio

Find a voice with the search box or the filters: Standard or Premium, gender and language. More filters narrows by age, use case, personality and speaking style.

Creating a Voiceover

1. Select the character who should speak. For narration without a character, click an empty part of the canvas so nothing is selected
2. Click Lip Sync in the character’s toolbar, or press Ctrl+Shift+L (Cmd+Shift+L on a Mac) to open the Lip Sync panel
3. Click Text to Speech
4. Type or paste your script (up to 3,000 characters per clip)
5. Choose a voice
6. Adjust the delivery if needed
7. Click Generate, listen to the result, and click Regenerate if you want another take
8. Click Add to Timeline

The clip is added at the playhead. If a character is selected, the voiceover is attached to it and the character lip-syncs to it. With nothing selected, it is added to the scene as narration.

Tip

Break long scripts into shorter sections. This gives you more control over timing and makes editing easier.

Type your script, choose a voice and generate. The character lip-syncs to it.

Voice Settings

Delivery (Standard voices)

• Speed: from 0.5× to 2×. Slower suits complex explanations, faster suits quick updates
• Pitch: lower for authoritative content, higher for energetic content
• Volume
• Speaking style and Style intensity: on voices that support styles

Voice settings (Premium voices)

• Stability, Similarity and Expression
• Speed
• Speaker boost

Pauses and emphasis

• Pause: insert a Short (250 ms), Medium (500 ms) or Long (1 second) pause anywhere in the script
• Say it (Standard voices): select words and choose Emphasise, Soften, Spell out, As number or As date to control how they’re read
• Perform (Premium v3 voices): add performance tags such as laughs, whispers, sighs, applause or [excited]

Best Practices

1. Write for speech: Use conversational language, not formal writing
2. Read aloud first: Test your script by reading it yourself
3. Use punctuation: Periods and commas create natural pauses
4. Keep sentences short: Easier to follow and sound more natural
5. Preview often: Listen to generated audio before finalizing

Syncing with Animation

1. Generate your voiceover first
2. Add it to the timeline
3. Adjust visual timing to match audio cues
4. Use the waveform on the audio clip to align animations
5. Fine-tune transitions to key phrases

Note

Audio clips on the timeline show their waveform, making it easy to see where words and pauses occur. To fine-tune a character’s lip-sync, open Mouth shapes from its toolbar.

Subtitles

Turn your narration into captions with the Subtitle panel: generate subtitles automatically, style them with 51 caption presets, and translate them into 20 languages.

Alternatives

If Text-to-Speech doesn’t fit your needs:

• Record your own voice: use Record in the Lip Sync panel, and your character lip-syncs to it
• Upload custom audio: upload an MP3 from the Lip Sync or Upload panel
• Music only: Use background music from the Audio panel without narration
• Silent videos: Some content works with text overlays only

Related Features

• Quick Start - Basic video creation
• Whiteboard Videos - Narration-heavy format
• Create First Animation - Full workflow