CallMissed logoCallMissed
Back to all models
Text to Speechenglishstreamingvoice-agents
Deepgram — deepgram-flux-tts logo

Deepgram Flux TTS

by Deepgram · Released 2026

Deepgram Flux TTS — streaming-first text-to-speech built for voice agents: turn-based synthesis with prosody carried across turns. 12 English voices including an Indian-accented one. English only, no expressive controls. $0.30 per 10K characters.

Deepgram — deepgram-flux-tts logo
Text to Speech

Deepgram Flux TTS

Powered by Deepgram · Streaming turn-based neural TTS

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Flux TTS is Deepgram's streaming-first text-to-speech model, designed around the way a voice agent actually speaks: in turns, not in one long block of narration. Synthesis is turn-based, and prosody carries across turns, so the agent's intonation and pacing stay continuous over a conversation instead of resetting on every reply.

Twelve English voices are available: Alexis, Bruce, Cole, Drew, Haley, Heather, Jack, Marcus, Priya, Renee, Rufus, and Sharon. Priya is Indian-accented English; the rest cover a range of American English personas. Select one by passing its name as the voice parameter.

The model is English-only, with multilingual coverage planned for a later release, and it carries no expressive, emotion, or style controls — delivery is what the model produces rather than something you dial in. On the CallMissed API it is reachable through the text-to-speech endpoint (POST /v1/audio/speech). It is not selectable for the live voice agent — use one of the other TTS models there. Billed at $0.30 per 10K characters.

Pricing

MetricPrice
Price /10K chars₹30.0000

1 credit = ₹1 = $0.01 USD. Prices shown from provider; CallMissed passes through with ~35% markup.

Key Highlights

  • Streaming-first, turn-based synthesis
  • Prosody carried across turns
  • 12 English voices, including Indian-accented English (Priya)
  • English only, no expressive controls

Benchmarks

BenchmarkScore
Voices12
LanguagesEnglish
Price$0.30

Technical Details

  • Streaming-first text-to-speech built for voice agents
  • Turn-based synthesis with prosody carried across turns
  • Voices: Alexis, Bruce, Cole, Drew, Haley, Heather, Jack, Marcus, Priya, Renee, Rufus, Sharon
  • Priya is Indian-accented English
  • English only — multilingual coverage planned for a later release
  • No expressive, emotion, or style controls
  • Available on CallMissed through the text-to-speech endpoint; not selectable for the live voice agent

Strengths

  • Turn-based streaming keeps first-audio latency low for conversation
  • Prosody continuity across turns — the agent does not reset its delivery every reply
  • 12 English voices including an Indian-accented option

Limitations

  • English only — multilingual coverage is planned for a later release
  • No expressive, emotion, or style controls
  • Available through the text-to-speech endpoint only; not selectable for the live voice agent
  • Paid plans only (not in the free tier)

Use Cases

Voice agent speech outputConversational IVRCustomer service botsReal-time English readouts

API Example

curl https://api.callmissed.com/v1/audio/speech \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -d '{"model": "deepgram-flux-tts", "input": "Thanks for holding — I have your order right here.", "voice": "priya"}' \
  --output speech.mp3

Endpoint: POST /v1/audio/speech · Model ID: deepgram-flux-tts

Try Deepgram Flux TTS now

Get 1000 free API credits on signup. No credit card required.

Start free Book a DemoRead docs