WTN SuiteWTN Suite

Edge-TTS

Generate speech audio using Microsoft Azure text-to-speech voices

Edge-TTS

Edge-TTS uses Microsoft Azure's text-to-speech service to convert your narration scripts into natural-sounding audio. It's available on all subscription plans and supports 50+ languages.

Features

  • Multi-language support — English, Spanish, French, German, Japanese, Korean, Chinese, and many more
  • Multiple voices per language — male and female voice options
  • Speech rate control — adjust speed from 0.5x to 2.0x
  • Real-time preview — listen to generated audio before saving
  • Single and batch generation — process one line or an entire script
  • Free with all plans — no additional API costs

Single Generation

Generate audio for a single piece of text:

  1. Open the Tool Suite panel → select Edge-TTS
  2. Type or paste your text in the input field
  3. Select a Language from the dropdown
  4. Choose a Voice (options change based on selected language)
  5. Adjust Speech Rate if needed (default: 1.0x)
  6. Click Generate to create the audio
  7. Use the Play button to preview, then Save to export

Batch Generation

Process an entire narration script at once:

  1. Prepare a text file with one line per audio segment
  2. In Edge-TTS, click Load Text File
  3. Configure language, voice, and speech rate
  4. Select an Output Folder
  5. Click Batch Generate — each line becomes a separate audio file
  6. Monitor progress in the progress bar

Output Formats

  • MP3 — smaller file size, good for web and general use
  • WAV — uncompressed, best quality for video production

Edge-TTS vs. Kokoro-TTS

| Feature | Edge-TTS | Kokoro-TTS | |---------|----------|------------| | Availability | All plans | Standard & Pro | | Processing | Cloud (requires internet) | Local (runs on your machine) | | Languages | 50+ languages | English (primary) | | Voice quality | Good (Azure neural voices) | Excellent (neural TTS) | | Speed | Fast (cloud processing) | Depends on hardware (GPU recommended) | | Cost | Free (included) | Free (included) |

Tips

  • For the best results with video narration, use a consistent voice throughout a chapter
  • Adjust speech rate to match the pacing of your content — action scenes may benefit from slightly faster narration
  • Preview audio before batch processing to ensure the voice and rate settings are right
  • Edge-TTS requires an internet connection — for offline processing, use Kokoro-TTS instead