Models & Languages Overview

Start with Flux TTS. It’s our best-sounding, most accurate model and the default recommendation for every use case it serves. Flux TTS is English-only today — for Spanish, German, French, Dutch, Italian, or Japanese, use Aura-2 until Flux TTS’s multilingual voices ship.

To request a voice, set the model to the voice you want. Aura-2 and Aura use /v1/speak:

Flux TTS uses /v2/speak (streaming WebSocket and batch REST). See Getting Started with Flux TTS.

Flux TTS is Deepgram’s best text-to-speech model and the recommended choice for every English use case — real-time voice agents, customer service, IVR, and pre-rendered audio alike. It’s conversation-native: streaming-first, turn-based, expressive by default, and consistent across turns, with native interruption handling and strong accuracy on the strings that trip up agents in production (alphanumerics, drug names, and other hard-to-say entities). Model strings follow the format flux-{voice}-{language} (e.g. flux-alexis-en), and model is required on every /v2/speak connection.

See the full Flux TTS Voices & Languages catalog for every voice and its characteristics.

Aura-2 is Deepgram’s widest-language text-to-speech model, with voices across seven languages. Reach for it when you need synthesis in a language Flux TTS doesn’t cover yet; for English, build on Flux TTS. Model strings follow the format aura-2-{voice}-{language} (e.g. aura-2-thalia-en).

See the full Aura Voices & Languages catalog for every voice, accent, and audio sample. Select Spanish voices (Aquila, Carina, Diana, Javier, Selena) support English–Spanish codeswitching.

Aura is Deepgram’s first-generation text-to-speech model. English voices only, served on /v1/speak.

See the Aura Voices & Languages catalog for the full list.