🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

GPT-4o Transcribe vs Whisper v1

vs

Which one, when — curated verdict, not a benchmark table

These bill in different units — whisper-1 at $0.006 per audio minute, gpt-4o-transcribe at $6 per million audio input tokens plus $2.5 and $10 per million text tokens — so no single conversion between them is honest. whisper-1 is the one with word- and segment-level timestamps, srt/vtt output and the translations endpoint, but it does not stream; gpt-4o-transcribe streams, including realtime transcription sessions, and returns json or text only. Pick whisper-1 for subtitles and translation, gpt-4o-transcribe for live transcripts.

Pricing

GPT-4o Transcribe Whisper v1 Δ
Per audio minute $0.006
Audio input / 1M tokens $6
Text output / 1M tokens $10

These two models bill in different units, so no Δ is shown — converting between them would require an assumption we have not measured. Each card is listed in its own unit above.

Capabilities

GPT-4o Transcribe Whisper v1
Speaker diarization no no
Streaming yes no
Timestamps no yes

Specs

GPT-4o Transcribe Whisper v1
Input modalities text audio audio
Output modalities text text
Released 2025-03-20 2023-03-01
Knowledge cutoff 2024-06
Limits

mp3/mp4/mpeg/mpga/m4a/wav/webm, up to 25MB

streaming transcription supported (incl. Realtime transcription sessions)

json/text output only

no word timestamps or diarization

mp3/mp4/mpeg/mpga/m4a/wav/webm, up to 25MB

word- and segment-level timestamps (verbose_json), srt/vtt output

no streaming

only model supported on the translations endpoint (to English)

Languages

57 languages listed for the transcriptions endpoint (one shared list for all transcription models)

ISO 639-1 / 639-3 codes accepted for GPT-4o-based models

Trained on 98 languages

57 listed as supported, the languages that met OpenAI's under-50% word-error-rate threshold across the transcriptions and translations endpoints

Max output 2K

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: GPT-4o Transcribe · Whisper v1

Switch between them with one line

Both ids are in every tab below — the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.audio.transcriptions.create(
    model="gpt-4o-transcribe",
    # model="whisper-1",  # uncomment this line, comment the one above
    file=open("meeting.mp3", "rb"),
    language="en",
)
print(resp.text)

Get an API key →

FAQ

Which is cheaper, GPT-4o Transcribe or Whisper v1?

They bill in different units, so there is no single honest number: GPT-4o Transcribe and Whisper v1 each appear in their own unit in the table above. Compare them on your own workload — the practical trade-off is described in the verdict at the top of this page.

Can I A/B test GPT-4o Transcribe against Whisper v1 without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key — switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.

Do GPT-4o Transcribe and Whisper v1 support speaker diarization?

The capability table above answers this per model, straight from each vendor’s documentation — diarization, streaming and timestamps are listed separately because models differ on all three.

Related comparisons

From our measured studies