Flux TTS Voices & Languages

Flux TTS voices use the model string format flux-{voice}-{language} (e.g. flux-haley-en). The same voice catalog is served on both /v2/speak transports — the streaming WebSocket and batch REST.

Pass the model string on connection:

wss://api.deepgram.com/v2/speak?model=flux-haley-en

Every voice handles general conversational synthesis. Use the tables below to shortlist, then hear the voices live at talk.deepgram.com before you build.

Start here. The featured voices are the strongest all-rounders in the catalog — the most versatile across customer service, IVR, narration, and casual chat. Browse More voices below for additional accents, ages, and characters when you're matching a specific brand or audience.

The rest of the catalog. Every voice here handles general conversational synthesis; the featured voices above are the strongest all-rounders.

Flux TTS voices speak English, with accents spanning American, British, Irish, Australian, Indian, Singaporean, and Filipino English. For synthesis in other languages, see Aura-2.

• Getting Started (Streaming) — connect and synthesize with a voice
• Getting Started (Batch) — one-shot synthesis
• Feature Overview
• Migrating from Aura to Flux TTS