Models

The list of models will be updated.

Available Models

  • Nanonets_Ocr_S_F16 (img2txt) – Lightweight OCR model by Nanonets for fast and accurate image-to-text extraction.

  • WhisperLargeV3 (audio2text) – Advanced speech recognition model by OpenAI for high-accuracy audio transcription.

  • Kokoro (txt2audio) – Expressive text-to-speech model designed for natural, emotional voice synthesis.

  • Flux1schnell (txt2img) – High-speed text-to-image generation model optimized for quick visual outputs.

PreviousQuickstartNextPricing (soon)

Last updated