by Fish Audio·Released 29 July 2026
S2 Pro reads text aloud in 80+ languages and takes direction in plain words inside square brackets, so a line can be whispered or excited. It handles multi-speaker conversations and expressive narration, with about 100 milliseconds to the first sound. It is the previous generation: S2.1 Pro improves quality and speed and adds voice cloning, so keep S2 Pro only for scripts already tuned to it.
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 |
|---|---|---|
| UTF-8 bytes | 4 992,53 DA |
per 1M UTF-8 bytes
One company runs this model. OpenDunes sends every request to it. DA per 1M UTF-8 bytes: ↑ what you send.
| Provider | ↑ Sent | Latency | Uptime |
|---|---|---|---|
| Fish Audio | 4 992,53 | … | … |
You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.
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="fish-audio/s2-pro",
input="مرحبا بكم في متجرنا. التوصيل مجاني في وهران.",
voice="alloy",
) as resp:
resp.stream_to_file("speech.mp3")Runs this request once on your balance.
About 3,00 DA per paragraph read aloud. ↑ 4 992,53 DA per 1M UTF-8 bytes. Arabic text takes about two bytes a character.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
S2 Pro reads text aloud in 80+ languages and takes direction in plain words inside square brackets, so a line can be whispered or excited. It handles multi-speaker conversations and expressive narration, with about 100 milliseconds to the first sound. It is the previous generation: S2.1 Pro improves quality and speed and adds voice cloning, so keep S2 Pro only for scripts already tuned to it.
Deposit dinars with your Edahabia or CIB card. Every model, S2 Pro included, is paid from that balance. No foreign card, no conversion.
Fish Audio says it supports 80+ languages with automatic detection. Arabic, French and Darja are not named for this model.
Voices: not stated. Cloning from a sample: not stated.
Fish Audio. Released 29 July 2026.
#4 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
Transcribes audio with automatic language detection and, when alignment details are asked for, timestamped word-level segments; the general Fish Audio transcription model, where Transcribe 1 Pro adds speaker labels
Transcribes interviews, meetings and podcasts, marking each speaker inline, keeping emotion and vocal cues such as laughter, detecting the language and returning timestamped words; the Pro tier of Transcribe 1
#5 for realistic voice · Fish Audio's production-grade successor to S2 Pro, for multilingual voice apps, narration and dialogue, taking open-ended direction on style and emotion in plain words and cloning a voice from a reference
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Clones a voice No.
Voice a two-person dialogue for a podcast trailer
Narrate an audiobook chapter with whispered lines
Read the same script in several languages