Deploy Models Now with NVIDIA NIM
Optimized inference for the world’s leading modelsFree serverless APIs for development
Self-Host on your GPU infrastructure
Continuous vulnerability fixes
Speech enhancing AI models for common voice degradations.
Enhance speech by correcting common audio degradations to create studio quality speech output.
Removes unwanted noises from audio improving speech intelligibility.
Connect generative AI models to speech by transcribing spoken audio to text.
Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.
Accurate and optimized English transcriptions with punctuation and word timestamps
Record-setting accuracy and performance for English transcription.
State-of-the-art accuracy and speed for English transcriptions.
Multi-lingual model supporting speech-to-text recognition and translation.
High accuracy and optimized performance for transcription in 25 languages
Robust Speech Recognition via Large-Scale Weak Supervision.
Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.
Record-setting accuracy and performance for Mandarin English transcriptions.
Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.
Voice generative AI models by converting written text to spoken audio.
Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.
Expressive and engaging text-to-speech, generated from a short audio sample.
Expressive and engaging text-to-speech, generated from a short audio sample.
Create multilingual generative AI models by translating speech and text between languages.
Translation model in 12 languages with few-shots example prompts capability.
Enable smooth global interactions in 36 languages.
Multi-lingual model supporting speech-to-text recognition and translation.
Robust Speech Recognition via Large-Scale Weak Supervision.