Skip to content

Text-to-Speech (TTS) ​

Generate natural, expressive AI voiceovers from transcripts, translated subtitles, or custom script text.


Features ​

  • Multi-Role Voices: Select from a diverse palette of male, female, neutral, and expressive AI voice personas.
  • Speed & Pitch Control: Fine-tune speaking rate from 0.5x to 2.0x for optimal video synchronization.
  • Dual-Language & Localization Dubbing: Convert translated foreign subtitles into natural spoken dialogue.
  • Audio Export: Export standalone high-bitrate .mp3 or .aac voiceover tracks ready to drop into Final Cut Pro or Premiere.

Supported TTS Engines ​

  • OpenAI TTS (tts-1, tts-1-hd with alloy, echo, fable, onyx, nova, shimmer)
  • Edge TTS (Natural multilingual neural voices)
  • CosyVoice / Custom Self-Hosted Engines
  • Apple Speech Synthesis (macOS built-in Siri & system voices)

Released under the MIT License.