Models
One name per model, however many providers serve it.
Deepgram: Flux TTS
Accepts- Text
Creates- Audio
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.
deepgram/flux-ttsAug 12, 202636 voicesMP3 · WAV16,218 Toman per 1,000 charactersDeepgram: Aura-2
Accepts- Text
Creates- Audio
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.
deepgram/aura-2Jul 16, 202690 voicesMP3 · WAV10,812 Toman per 1,000 charactersDeepgram: Nova-3
Accepts- Audio
Creates- Text
Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
deepgram/nova-3Jul 15, 2026With segment and word times1,550 Toman a minute of audio
3 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

