Skip to content
OmniRail
← All models

Deepgram · Voice model

Flux TTS

deepgram/flux-tts
  • Voice
Released Aug 12, 2026

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.

Specifications

Input
text, up to 20,000 characters per call
Output
mp3 (default) or raw pcm
Voice
`voice`, default flux-alexis-en · flux-alexis-en, flux-bree-en, flux-brittany-en, flux-brooke-en, flux-bruce-en, flux-cliff-en, flux-cole-en, flux-colin-en, flux-conor-en, flux-donovan-en, flux-drew-en, flux-elise-en, … (36 in all)
Billing
per character of input text

Use it

POST /api/v1/audio/speech · MCP speak · full reference

curl https://omnirail.org/api/v1/audio/speech \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"deepgram/flux-tts","input":"Hello from OmniRail. Every model, one key.","response_format":"mp3"}' \
  --output hello.mp3