CATALOG

Models

Find the right model by capability, context and price. Compare options or try one in Chat.

Output / endpointExact metadata
4 of 647 modelsReference token prices are per million tokens.
Free

CLSSAI has not normalized curated metadata for this model ID yet. Confirm current availability in the live model directory before using it in production.

by deepgramAug 12, 2026— context— input— outputPending → Pending

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.

by deepgramJul 16, 2026N/A contextSpecialized media pricing · open model detailsText → Speech
Audio input

Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.

by deepgramJul 15, 2026N/A contextSpecialized media pricing · open model detailsAudio → Transcription

Flux TTS is a text-to-speech model from Deepgram. It is suited for natural, expressive English speech synthesis across Deepgram's Flux voice catalog.

by deepgramAug 12, 2026N/A contextSpecialized media pricing · open model detailsText → Speech