opendunes

Flux TTS

by DeepgramReleased 12 August 2026

Flux TTS turns English text into speech built for live conversation, with 36 voices across seven accents. Delivery is expressive by default, so a voice agent sounds like it is replying, not reading. Use it for voice agents, phone support and general English narration in a new build.

TakesText
GivesAudio
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 8,99 DA per paragraph read aloud3 000 DA buys about 330 paragraphs read aloud

One paragraph read aloud, the ordinary use

600 characters sent× 14 977,60 DA per 1M8,99 DA
Total≈ 8,99 DA

Every rate

Meter↑ you send↓ comes back
Characters14 977,60 DA

per 1M characters

Speak a 200-character chatbot reply aloud in a natural voice≈ 3,00 DA
Narrate a 500-character product demo script in a chosen catalog voice≈ 7,49 DA
Voice a 1,000-character podcast intro as expressive English audio≈ 14,98 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the text.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M characters: ↑ what you send.

Deepgram…
↑
14 977,60
Latency
…
Provider↑ SentLatencyUptime
Deepgram14 977,60……

You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/audio/speech
Base URL
https://opendunes.com/v1
Model ID
deepgram/flux-tts
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

with client.audio.speech.with_streaming_response.create(
    model="deepgram/flux-tts",
    input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
    voice="flux-alexis-en",
) as resp:
    resp.stream_to_file("speech.mp3")
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Questions about Flux TTS

  • How much does Flux TTS cost in dinars?

    About 8,99 DA per paragraph read aloud. ↑ 14 977,60 DA per 1M characters.

  • Is Flux TTS free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Flux TTS best for?

    Flux TTS turns English text into speech built for live conversation, with 36 voices across seven accents. Delivery is expressive by default, so a voice agent sounds like it is replying, not reading. Use it for voice agents, phone support and general English narration in a new build.

  • How do I pay for Flux TTS without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Flux TTS included, is paid from that balance. No foreign card, no conversion.

  • Does Flux TTS work in Arabic, French or Darja?

    Deepgram names no languages for Flux TTS. Arabic, French and Darja: not stated.

  • How many voices, and can it clone mine?

    36 voices. Cloning from a sample: not stated.

  • Who makes Flux TTS, and when was it released?

    Deepgram. Released 12 August 2026.

Other Deepgram models, priced in dinars

See all Deepgram models
Nova-3Deepgram · Jul 15, 2026

Nova-3 takes an audio recording and gives back the written transcript. It copes with speech in noisy places such as call centres and drive-thrus, and it can follow a conversation that switches between languages, among them English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian and Dutch. Use it to transcribe support calls, meetings and voice notes, live or from files. It only writes text; to speak text back, pair it with Aura-2 or Flux TTS.

1,43 DAper minute of audio
View model
Aura-2Deepgram · Jul 16, 2026

Aura-2 turns text into speech in more than 40 voices from Deepgram, and it is the Deepgram choice when the language is not English: Spanish, German, French, Dutch, Italian and Japanese are covered. It starts speaking in under 200 milliseconds, which suits phone agents, automated menus and customer-service bots. For English-only builds with more expressive delivery, Flux TTS is the newer voice; Orpheus 3B fits English storytelling.

90 voices
≈5,99 DAper paragraph read aloud
View model