Models & Languages Overview

An overview of Deepgram’s text-to-speech models and supported languages.

Models

ModelDescription & Use
Flux TTSOur latest-generation, conversation-native voice model — streaming-first, turn-based, and expressive by default. Recommended for all new builds: voice agents, customer service, IVR, and general-purpose synthesis. Served on /v2/speak.
Aura-2Our widest-language model, with voices across seven languages. Recommended when you need synthesis in a language Flux TTS doesn’t cover yet. Served on /v1/speak.
AuraOur first-generation text-to-speech model. English voices only. Served on /v1/speak.

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.

All models default to language=en (via the voice’s model string). A model is required on every request — Flux TTS on /v2/speak, Aura-2 and Aura on /v1/speak.

Example

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

cURL (Aura-2, /v1/speak)
$curl "https://api.deepgram.com/v1/speak?model=aura-2-thalia-en" \
>  -H "Authorization: Token YOUR_DEEPGRAM_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{ "text": "Hello, how are you?" }' \
>  --output audio.mp3

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

Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

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.

Model OptionLanguage
flux-{voice}-enEnglish (American, British, Irish, Australian, Indian, Singaporean, Filipino): en

Multilingual voices (flux-{voice}-multi) are planned for a later release. See the full Flux TTS Voices & Languages catalog for the launch voices and their characteristics.

Aura-2

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).

Model OptionLanguage
aura-2-{voice}-enEnglish (American, British, Australian, Filipino): en
aura-2-{voice}-esSpanish (Mexican, Peninsular, Colombian, Argentine, Latin American): es
aura-2-{voice}-deGerman: de
aura-2-{voice}-frFrench: fr
aura-2-{voice}-nlDutch: nl
aura-2-{voice}-itItalian: it
aura-2-{voice}-jaJapanese: ja

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

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

Model OptionLanguage
aura-{voice}-enEnglish (American, British, Irish): en

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