#1 for speech · Gemini 3.8 Flash TTS turns text into speech in 130+ languages with studio-grade acting, regional accents and a voice that stays consistent through long dialogues. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for audiobooks, narration and multi-speaker scenes.
Simba 3.5
Newby SpeechifyReleased 11 November 2026
Speechify: Simba 3.5 turns written text into spoken audio, reading your words aloud in any of 48 languages, with the language chosen each time you ask. It speaks through 20 ready-made voices, so you can sit down and have a book, an article or a website read out to a listener in seconds. Speech is streamed as it is made, so a listener hears the words without waiting for the whole recording. It cannot copy a person's own voice, so a job that needs a cloned voice needs a different kind of model.
Where your request runs
One company runs this model. OpenDunes sends every request to it. DA per 1M characters: ↑ what you send.
You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.
What it costs
You pay for what each request uses. No subscription, no minimum.
One paragraph read aloud, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Characters | 4 992,53 DA |
per 1M characters
Everyday jobs, priced
- 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.
Call it in code
Swap the base URL and the key. Your OpenAI code runs unchanged.
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="speechify/simba-3.5",
input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
voice="geffen_32",
) as resp:
resp.stream_to_file("speech.mp3")Runs this request once on your balance.
Limits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- not stated
- Max output
- not stated
- Reads at once
- not stated
- Longest reply
- not stated
- Tokenizer
- Other
- Released
- 11 Nov 2026
Questions about Simba 3.5
How much does Simba 3.5 cost in dinars?
About 3,00 DA per paragraph read aloud. ↑ 4 992,53 DA per 1M characters.
Is Simba 3.5 free? Can I try it?
No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.
What is Simba 3.5 best for?
Speechify: Simba 3.5 turns written text into spoken audio, reading your words aloud in any of 48 languages, with the language chosen each time you ask. It speaks through 20 ready-made voices, so you can sit down and have a book, an article or a website read out to a listener in seconds. Speech is streamed as it is made, so a listener hears the words without waiting for the whole recording. It cannot copy a person's own voice, so a job that needs a cloned voice needs a different kind of model.
How do I pay for Simba 3.5 without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, Simba 3.5 included, is paid from that balance. No foreign card, no conversion.
Does Simba 3.5 work in Arabic, French or Darja?
Speechify names no languages for Simba 3.5. Arabic, French and Darja: not stated.
How many voices, and can it clone mine?
20 voices. Cloning from a sample: not stated.
Who makes Simba 3.5, and when was it released?
Speechify. Released 11 November 2026.
Similar models, priced in dinars
See all modelsFlash Lite TTS from the 3.8 family turns text into speech in 101 languages, built for large volumes of audio, live voice assistants and read-aloud features. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for speed and volume.
Google's preview of 3.1 Flash TTS turns text into speech using Google's prebuilt voices. It is the earlier generation of Gemini speech: Google now points users to Gemini 3.8 Flash TTS for acted-out expression and long multi-turn dialogue, and to 3.8 Flash-Lite TTS for volume. Keep this one only for workflows that write style directions into the text, which the 3.8 models expect as separate settings.
#5 for realistic voice · Drama 3 performs a script the way you direct it, reading plain-language stage directions in square brackets before each line, with sighs, pauses and whispered words placed exactly where you write them
