Audio-to-Audio
Speech-to-speech models that consume and generate audio.
Classification follows the Hugging Face task taxonomy. See the Hugging Face Audio-to-Audio task page for the ecosystem-level task definition.
Model families
| Model family | Declared recipes | Exact checkpoint examples | Runtime CLI |
|---|---|---|---|
personaplex | 3 | nvidia/personaplex-7b-v1 | trtmc speak |