Deepgram
Deepgram: Aura-2
deepgram/aura-2
Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.
Input
$30
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
Not published
tokens
Speech output · Token reference fields do not establish an output-unit price.
Model facts
Author
Deepgram
Tokenizer
Other
Modality
Text -> Speech
Created
Jul 16, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextOutput · Speech