EVI 3

Published

May 29, 2025

EVI 3 is an AI model developed by Hume (United States), first published in May 2025. It works in the speech domain, on tasks such as speech-to-text, speech recognition (asr), speech synthesis and 4 more.

Epoch AI has no training-compute estimate for this model.

Access: API access. Its weights are not openly released.

Full record

Organization: Hume
Country of organization: United States
Domain: Speech
Task: Speech-to-text, Speech recognition (ASR), Speech synthesis, Text-to-speech (TTS), Retrieval-augmented generation, Audio question answering, Speech-to-speech
Model accessibility: API access
Open weights: No