opendunes

Transcribe 1 Pro

by Fish AudioReleased 24 September 2026

Transcribe 1 Pro transcribes interviews, meetings and podcasts, labelling each speaker in the text and marking emotion and vocal sounds. It handles recordings up to 60 minutes. Plain Transcribe 1 is enough for a short clip with one voice.

TakesAudio
GivesText

Where your request runs

One company runs this model. OpenDunes sends every request to it.

Fish Audio…
Per second of audio
0,033 DA
Latency
…
ProviderPer second of audioLatencyUptime
Fish Audio0,033 DA……

You pay the price of the provider that served your request. Prices read 02:48 · speed over the last 30 minutes · uptime over 3 days.

What it costs

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

2,00 DA per minute of audio3 000 DA buys 1 500 minutes of audio

One minute of audio, the ordinary use

60 sent60 seconds of audio sent× 0,033× 0,033 DA2,00 DA
Total2,00 DA

Every rate

Meter↑ you send↓ comes back
Second of audio0,033 DA

per second of audio sent

Everyday jobs, priced

Transcribe a 2-minute voice note≈ 3,99 DA
Transcribe a 20-minute interview≈ 39,94 DA
Transcribe a 30-minute meeting≈ 59,91 DA
Transcribe a 45-minute podcast≈ 89,87 DA
Transcribe a one-hour panel talk≈ 119,82 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length of the audio.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

Call it in code

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

POST /v1/audio/transcriptions
Base URL
https://opendunes.com/v1
Model ID
fish-audio/transcribe-1-pro
import os
from openai import OpenAI

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

with open("meeting.mp3", "rb") as f:
    resp = client.audio.transcriptions.create(model="fish-audio/transcribe-1-pro", file=f)

print(resp.text)

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
24 Sep 2026
Full API reference

Questions about Transcribe 1 Pro

How much does Transcribe 1 Pro cost in dinars?

About 2,00 DA per minute of audio. ↑ 0,033 DA per second of audio.

Is Transcribe 1 Pro 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 Transcribe 1 Pro best for?

Transcribe 1 Pro transcribes interviews, meetings and podcasts, labelling each speaker in the text and marking emotion and vocal sounds. It handles recordings up to 60 minutes. Plain Transcribe 1 is enough for a short clip with one voice.

Transcribe 1 Pro or Transcribe 1?

Transcribe 1 costs the same for the same minute of audio.

How do I pay for Transcribe 1 Pro without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Transcribe 1 Pro included, is paid from that balance. No foreign card, no conversion.

Does Transcribe 1 Pro work in Arabic, French or Darja?

Fish Audio names no languages for Transcribe 1 Pro. Arabic, French and Darja: not stated.

Does it say who spoke, and when?

Speaker labels: yes. Word timings: not stated.

How long can a file be?

Up to 25 MB as an upload. Longer audio goes in the request body.

Who makes Transcribe 1 Pro, and when was it released?

Fish Audio. Released 24 September 2026.

Other Fish Audio models, priced in dinars

See all Fish Audio models
Drama 3Fish Audio · Oct 13, 2026

#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

Clones a voice
≈2,00 DAper paragraph read aloud
View model
S2.1 ProFish Audio · Jul 29, 2026

#6 for realistic voice · S2.1 Pro is Fish Audio's recommended speech model for real products: it speaks 83 languages, detects the language itself, and takes open-ended direction in square brackets, such as a whisper. It handles multi-speaker dialogue and expressive narration, and supports voice cloning.

Clones a voice
≈3,00 DAper paragraph read aloud
View model
Transcribe 1Fish Audio · Jul 29, 2026

Transcribe 1 converts audio to text, detects the language by itself, and can mark when each word was said if you ask. It is aimed at shorter recordings. Pick it for quick clips and simple dictation.

2,00 DAper minute of audio
View model
S1Fish Audio · Jul 29, 2026

S1 turns text into speech in 13 languages, and you steer emotion with cues written in parentheses, 64+ expressions in all.

≈3,00 DAper paragraph read aloud
View model