Skip to main content
Turn text into natural-sounding speech using AI voice technology. Create voiceovers for videos, podcasts, training materials, phone systems, and more.

​
What Can You Create?

  • Video narration and voiceovers
  • Podcast intros and outros
  • Training and educational content
  • IVR phone messages
  • Audiobook content
  • Voice announcements
  • Accessibility audio versions of content

​
Creating Your First Audio

​
Step 1: Open Audio Generation

  1. Select your company from the sidebar
  2. Click Audio (under the Content Engine menu)
  3. Click Generate Audio (or the + button)

​
Step 2: Enter Your Text

Type or paste the text you want converted to speech:

​
Step 3: Choose a Voice

Browse available voices and pick one that fits your needs:
  • Male or female
  • Different accents (American, British, etc.)
  • Various personality types (friendly, professional, energetic)
You can choose from ready-made voices or select a custom voice you’ve cloned in the Voices section — your cloned voices appear right alongside the ready-made ones. Tip: Click the play button next to a voice to hear a sample.

​
Step 4: Adjust Settings

  • Speed: How fast the voice speaks (0.5x to 2x)
  • Model: Different AI models for varying quality

​
Step 5: Generate

  1. Click Generate
  2. Wait a few seconds
  3. Play your audio to review
Happy with it? Download and use it. Need changes? Adjust and regenerate.

​
Choosing the Right Voice

​
Voice Characteristics

​
Matching Voice to Content

​
Writing for Audio

Text written for reading doesn’t always sound natural when spoken. Here are tips for better audio:

​
Write Conversationally

❌ Written style: “The implementation of our solution facilitates operational efficiency.” ✅ Audio style: “Our solution makes your work faster and easier.”

​
Use Punctuation for Pacing

Punctuation affects how the AI reads your text:
  • Commas: Short pause
  • Periods: Medium pause
  • Dashes (—): Dramatic pause
  • Ellipses (…): Thoughtful pause
Example:

​
Spell Out Abbreviations

The AI might mispronounce abbreviations:
  • ❌ “CEO” might be read as “see-ee-oh”
  • ✅ “Chief Executive Officer” or write phonetically

​
Add Phonetic Hints for Unusual Words

For names or technical terms:

​
Adjusting Speed

The speed setting affects how fast the voice speaks: Tip: Most professional voiceovers use 0.9x to 1.1x speed.

​
Managing Your Audio Files

​
Viewing Your Library

All generated audio is saved automatically:
  1. Go to Audio
  2. Browse your list
  3. Click play to preview any file

​
Playing Audio

  1. Click on an audio file
  2. Use the play controls
  3. Adjust volume as needed

​
Downloading Audio

  1. Click on an audio file
  2. Click Download
  3. File saves as MP3 (most common) or other format

​
Deleting Audio

  1. Click the three-dot menu (⋮) on the audio file
  2. Select Delete
  3. Confirm

​
Tips for Better Audio

​
1. Break Long Text into Sections

Instead of one long script, create separate audio files for:
  • Intro
  • Main content sections
  • Call to action
  • Outro
This makes editing easier and allows mixing voices.

​
2. Test Before Full Production

Generate a short sample first to verify:
  • The voice sounds right
  • Speed is appropriate
  • Pronunciation is correct
  • Tone matches your content

​
3. Review and Re-Generate

Listen critically:
  • Does it sound natural?
  • Are pauses in the right places?
  • Is the emphasis correct?
Adjust text or settings and regenerate as needed.

​
4. Consider Your Audience

  • International audience: Choose a neutral accent
  • Technical content: Slower speed for comprehension
  • Young audience: More energetic voices

​
Audio Length Limits

Most models have character limits per generation: For longer content, split into multiple audio files.

​
Using Audio in Projects

​
Adding to Videos

  1. Download your audio file
  2. Import into your video editor
  3. Sync with visuals

​
Podcasts

  1. Generate intro/outro clips
  2. Create spoken content sections
  3. Combine in your audio editor

​
Phone Systems (IVR)

  1. Generate short, clear prompts
  2. Export in required format
  3. Upload to your phone system

​
Custom Voices

Want a unique voice that sounds like you or represents your brand? See Voices to learn about voice cloning.

​
Frequently Asked Questions

Q: How long does audio generation take? A: Usually 5-15 seconds for short clips, up to a minute for longer content. Q: What format are audio files? A: Typically MP3. Some systems offer additional formats. Q: Can I use these for commercial purposes? A: Yes, check your subscription terms for specific commercial use rights. Q: Why does the voice mispronounce a word? A: Try spelling it phonetically or differently. AI learns from common pronunciations. Q: Can I make the voice sound emotional? A: To some extent. Use punctuation and word choice to guide emotion. For more control, consider using custom Voices.

​
Next Steps