fal-ai

Minimax

fal/minimax-preview-speech-2.5-turbo

Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

  • Input: text
  • Output: speech

RuntimeWire coverage

  • MiniMax H3 generates a 10.125-second audiovisual file in under nine seconds
  • Modular open-sources Mojo three weeks after Qualcomm acquisition

View on OpenRouter. Model data sourced from OpenRouter.

More models from fal-ai

  • Heygen
  • Feynobg Background Remover
  • Krea 2 Text to Image Turbo Style
  • Krea 2 Turbo
  • Telestyle V2 Style Transfer
  • Scail 2

Browse all AI models