p2d
> open whisper --ru_

Whisper in Russia without a VPNWhisper Large V3, GPT Transcribe, and GPT-4o Transcribe in the P2D AI aggregator — audio-to-text transcription

OpenAI models convert speech to text: meetings, interviews, lectures, and voice messages. Pay via SBP, and pay only for minutes.

  • GPT Transcribe$0.009
  • Whisper Large V3$0.0009
  • Whisper Large V3 Turbo$0.0004
  • GPT-4o Transcribe$0.011
p2d://ai-agregator/whisper

> you: file: interview.m4a · 18 min

gpt-transcribe ▸

[ok] 18 min of audio transcribed · charged $0.16

The terminal shows how Whisper transcribes audio to text: a meeting, an interview, and a voice message, with the cost of each transcription.
> ls ./whisper

OpenAI transcription models in the aggregator

The aggregator has 6 OpenAI models for speech transcription:

  1. August 2026

    GPT Transcribenew

    High-accuracy OpenAI model for recordings and streaming audio.

    minute of transcription
    $0.009
    for $10
    ≈ 18 h
  2. May 2026

    Whisper Large V3

    The open Whisper model: transcription and translation of speech in many languages — very cheap.

    minute of transcription
    $0.0009
    for $10
    ≈ 185 h
  3. May 2026

    Whisper Large V3 Turbo

    Accelerated version of Whisper Large V3 — the most affordable.

    minute of transcription
    $0.0004
    for $10
    ≈ 416 h
  4. April 2026

    GPT-4o Transcribe

    High-quality transcription based on GPT-4o.

    minute of transcription
    $0.011
    for $10
    ≈ 14 h
  5. May 2026

    GPT-4o Mini Transcribe

    Economical version of GPT-4o Transcribe.

    minute of transcription
    $0.0057
    for $10
    ≈ 28 h
  6. April 2026

    Whisper 1

    Classic Whisper through the OpenAI API.

    minute of transcription
    $0.012
    for $10
    ≈ 13 h
> whisper --help

What Whisper can do

Meetings and calls

Text of a meeting or call — so you don't have to take notes by hand.

> Transcribe the recording of a call with a client

Interview

Transcription for journalists and researchers.

> Transcribe a 40-minute interview

Lectures

Lecture or webinar notes as text.

> Transcribe the webinar and split it by topic

Voice

Long voice messages — into text.

> Turn a voice message into text
> price whisper --beta 1.0

How much does audio transcription cost

No subscription: pay only for transcription. The price is from $0.0004 to $0.012 per minute of audio.

Beta 1.0 prices may change

Prices
ModelDeveloperMinute of audioHour of audio$10 is enough for
GPT TranscribeOpenAI$0.009$0.54≈ 18 h
GPT-4o Mini TranscribeOpenAI$0.0057$0.34≈ 28 h
Whisper Large V3OpenAI$0.0009$0.054≈ 185 h
Whisper Large V3 TurboOpenAI$0.0004$0.024≈ 416 h
Whisper 1OpenAI$0.012$0.72≈ 13 h
GPT-4o TranscribeOpenAI$0.011$0.69≈ 14 h

The price is per minute of audio recording. The actual transcription cost is deducted from your balance.

> cat ./how-to-start.txt

How to use Whisper in Russia

  1. 01

    Sign up for P2D

    One account opens all the aggregator's models — no need to register with each one separately.

  2. 02

    Top up your balance via SBP

    Balance in dollars. No foreign card or VPN needed, no monthly fee.

  3. 03

    Choose Whisper

    Open the AI aggregator, choose a model, and add an audio recording. The cost of the result is deducted from your balance.

Sign up and get started →
> man whisper

FAQ about Whisper

How to use Whisper in Russia?

Sign up for P2D, top up your balance via SBP, and choose Whisper in the AI aggregator. No VPN or foreign card needed.

Do you need a VPN for Whisper?

No. The P2D aggregator opens from Russia without a VPN, and the service itself sends the requests to the model.

How much does transcription cost in Whisper?

No subscription — you pay for minutes of audio. A minute with GPT Transcribe costs about $0.009, and an hour of recording about $0.54.

Is there a subscription for Whisper?

No subscription: you top up your balance in dollars and spend it only on what you generate. The same balance works for all of the aggregator's models.

Does Whisper understand Russian speech?

Yes, Whisper and GPT Transcribe models recognize Russian speech and many other languages.

How does GPT Transcribe differ from Whisper?

GPT Transcribe is OpenAI's new high-accuracy model; Whisper Large V3 is an open model that costs several times less. Whisper is often enough for clean recordings.

Does Whisper understand prompts in Russian?

Yes. Whisper recognizes Russian speech.

Other models in the aggregator

> start --whisper

Try Whisper right now

Sign up in a minute, top up via SBP, pay only for the result.

Start with Whisper →