OpenAI Whisper API

Name: OpenAI Whisper API
Price: 0.006 USD
Author: OpenAI

by OpenAI

OpenAI Whisper API is listed here under Transcription APIs. Skip the setup: WhipScribe transcribes it in your browser. Packs: $4 for 500 minutes, $12 for 2,000, $24 for 5,000; Workspace $19 a month. Up to 10 hours or 5 GB per file. Measured turnaround: about 2 minutes per audio hour. 99 languages. Checked 25 Oct 2026.

Don’t want to wire up OpenAI Whisper API? Drop the file here.

Every recording starts with a free preview of its opening minutes. Credits never expire.

OpenAI's hosted Whisper API — gpt-4o-transcribe is the newest model, gpt-4o-mini-transcribe is the cheaper sibling, whisper-1 is the legacy reference. One REST surface.

API · $0.006/min

whisper-1 is deprecated: it leaves the API on 26 February 2027

On 26 Aug 2026 OpenAI told developers that whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe (with its 2025-12-15 snapshot) and gpt-4o-transcribe-diarize will be removed from the API on 26 Feb 2027. The replacements it names are gpt-transcribe and gpt-live-transcribe.

Code that sends model=whisper-1 keeps working until then, and switching is one field: model=gpt-transcribe. Test the response first. The guide documents verbose_json and timestamp_granularities[] for whisper-1 only, so subtitle pipelines that depend on word times need checking before the move.

Model	Estimated price per minute	Status	Note
gpt-transcribe	$0.0045	Recommended for recorded speech	Returns the text and the detected languages
gpt-live-transcribe	$0.017	Recommended for live audio	Replacement for real-time use
whisper-1	$0.006	Deprecated, removed 26 Feb 2027	The only model the guide documents word timestamps for
gpt-4o-transcribe	$0.006	Deprecated, removed 26 Feb 2027
gpt-4o-mini-transcribe	$0.003	Deprecated, removed 26 Feb 2027
gpt-4o-transcribe-diarize	Not on the pricing page we read	Deprecated, removed 26 Feb 2027	Speaker segments through diarized_json

Sources:

OpenAI · Deprecations, fetched 26 Oct 2026
OpenAI · API pricing, fetched 26 Oct 2026
OpenAI · Speech to text guide, fetched 26 Oct 2026

A Whisper API call, the 25 MB limit and what an hour costs

Uploads stop at 25 MB, in mp3, mp4, mpeg, mpga, m4a, wav or webm; for longer recordings the guide says to compress the file or split it. By our arithmetic, 25 MB of 64 kbps MP3 is about 52 minutes. The API reference lists json, text, srt, verbose_json, vtt and diarized_json as output formats and says support depends on the model.

At OpenAI's estimates an hour costs $0.27 on gpt-transcribe and $0.36 on whisper-1. WhipScribe takes files up to 10 hours or 5 GB per file with no splitting, and its first pack is $4 (500 minutes); the 5,000-minute pack includes API access.

whisper-1 with word timestamps.

curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F file=@audio.mp3 \
  -F model=whisper-1 \
  -F response_format=verbose_json \
  -F "timestamp_granularities[]=word"

The same file on gpt-transcribe, the guide's example.

curl --request POST \
  --url https://api.openai.com/v1/audio/transcriptions \
  --header "Authorization: Bearer $OPENAI_API_KEY" \
  --header 'Content-Type: multipart/form-data' \
  --form file=@audio.mp3 \
  --form model=gpt-transcribe

Sources:

OpenAI · Speech to text guide, fetched 26 Oct 2026
OpenAI · API reference, create transcription, fetched 26 Oct 2026
OpenAI · API pricing, fetched 26 Oct 2026

TL;DR

OpenAI's hosted speech-to-text sits behind one endpoint, POST https://api.openai.com/v1/audio/transcriptions. whisper-1 ($0.006 a minute) and the gpt-4o transcribe models are deprecated and leave the API on 26 February 2027; for recorded audio OpenAI now recommends gpt-transcribe ($0.0045 a minute).

Uploads stop at 25 MB in mp3, mp4, mpeg, mpga, m4a, wav or webm. The guide documents word-level timestamps (timestamp_granularities[]) for whisper-1 only, and speaker segments only through gpt-4o-transcribe-diarize. Checked 26 Oct 2026 on OpenAI's own docs.

What it is

OpenAI's hosted transcription endpoint, POST https://api.openai.com/v1/audio/transcriptions. whisper-1 is the Whisper model behind it. On 26 Aug 2026 OpenAI announced that whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize leave the API on 26 Feb 2027, and named gpt-transcribe and gpt-live-transcribe as replacements. Files up to 25 MB. Prices checked 26 Oct 2026.

Best for: Teams already on OpenAI's stack who want Whisper without operating a GPU.
Watch out for: 25 MB per upload; whisper-1 and the gpt-4o transcribe models are removed on 26 Feb 2027; speaker labels only through gpt-4o-transcribe-diarize; upload time dominates on large files.

Install / use

POST https://api.openai.com/v1/audio/transcriptions

View OpenAI Audio API docs ↗

Where the Whisper API fits · 6 use-cases

OpenAI's audio surface is small but covers the common shapes: subtitles, translation, long-form chunking, real-time, telephony, and multilingual. Each card points at the matching section on platform.openai.com — pick the closest one and copy a recipe below.

Subtitles · VTT / SRT

response_format=srt or vtt

Pass response_format=srt or response_format=vtt to /v1/audio/transcriptions and the API returns a subtitle file directly — no client-side stitching. For finer timing pass response_format=verbose_json with timestamp_granularities=['segment','word'] to get per-segment and per-word offsets on whisper-1, the only model the speech-to-text guide documents it for.

whisper-1
verbose_json + timestamp_granularities for word-level offsets

Auto-translation to English

/v1/audio/translations

The sibling endpoint /v1/audio/translations transcribes non-English audio directly into English text in one call — useful when downstream tooling is English-only. Currently supported on whisper-1; for other source/target pairs run /transcriptions then a chat model.

whisper-1
Translation task is English-only output

Long-form audio · chunking

25 MB request cap

Files over 25 MB must be split client-side before upload. The OpenAI cookbook pattern uses pydub to slice on silence boundaries, transcribe each chunk in parallel, then concatenate. Alternative: compress to 16 kHz mono opus / m4a to fit a 60-90 min episode under 25 MB.

any model
Hard 25 MB cap per request — no server-side chunking

Real-time · live agents

Realtime API · WebSocket

For sub-second streaming STT use the Realtime API (gpt-4o-realtime-preview), not /audio/transcriptions — the REST endpoint is request/response only. Realtime carries bidirectional audio over WebSocket or WebRTC and is the path for voice agents, live captions, and IVR replacements.

gpt-4o-realtime-preview
Separate SKU and endpoint from /audio/transcriptions

Calls · voicemail · meetings

gpt-4o-mini-transcribe · cheapest

gpt-4o-mini-transcribe at $0.003/min is the budget pick for high-volume call recordings and voicemail batches where every cent matters and word-level timestamps are optional. No diarization in the response — pair with a downstream speaker-attribution model or a tool that bundles it.

gpt-4o-mini-transcribe
Half the per-minute cost of gpt-4o-transcribe and whisper-1

Multilingual · 50+ languages

Auto language detect

All three models auto-detect the input language; pass an ISO-639-1 language hint (e.g. language='ja') to skip detection and improve accuracy on short clips. Quality varies by language — large-v2 weights underneath whisper-1 are the same set the open-source Whisper community benchmarks against.

all 3 models
Optional language hint sharpens short-clip detection

Pattern: the hosted OpenAI surface is the right call when consolidation, GPT-4o-class accuracy on noisy audio, or zero ops matter more than raw price. If sub-second streaming + voice-agent loop is the product, Deepgram Nova-3 is closer to purpose-built. For self-hosted control on the same Whisper weights, see openai-whisper (reference) or faster-whisper (production swap-in). For a managed transcript with no API wiring, drop a file into Whipscribe.

Quickstart · pick a runtime

Three minimal calls to /v1/audio/transcriptions with gpt-4o-transcribe. Export your key as OPENAI_API_KEY first — get one from the OpenAI dashboard. Never hard-code the key in source.

1Python SDK · openai-python v2.x

Official openai Python SDK · transcribe a local file with gpt-4o-transcribe.

# pip install --upgrade openai
import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

with open("audio.mp3", "rb") as f:
    resp = client.audio.transcriptions.create(
        model="gpt-4o-transcribe",
        file=f,
        # response_format="verbose_json",
        # timestamp_granularities=["segment", "word"],  # whisper-1 + gpt-4o-transcribe
        # language="en",                                # ISO-639-1 hint
    )

print(resp.text)

Source: openai/openai-python ↗ · API reference: platform.openai.com/docs/api-reference/audio/createTranscription ↗

2Node SDK · openai-node v4+

Official openai Node / TypeScript SDK · same call from Node 18+.

// npm install openai
import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

const resp = await client.audio.transcriptions.create({
  model: "gpt-4o-transcribe",
  file: fs.createReadStream("audio.mp3"),
  // response_format: "verbose_json",
  // timestamp_granularities: ["segment", "word"],
  // language: "en",
});

console.log(resp.text);

Source: openai/openai-node ↗

3cURL · multipart/form-data

Plain HTTPS POST to /v1/audio/transcriptions · works from shell, CI, and edge runtimes.

# Bearer auth via $OPENAI_API_KEY · multipart upload
curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F file="@audio.mp3" \
  -F model="gpt-4o-transcribe"

# Subtitle output: add -F response_format="srt"
# Word timestamps (whisper-1 / gpt-4o-transcribe):
#   -F response_format="verbose_json" \
#   -F "timestamp_granularities[]=word" -F "timestamp_granularities[]=segment"

Source: platform.openai.com/docs/api-reference/audio/createTranscription ↗

What people actually do with OpenAI Whisper API-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Transcribe a whole back catalogue in one runThe archive is the asset, but one-at-a-time upload means it never gets done.…1,000 hours ≈ $480, onceTranscribe every new file in a Drive folderFiles accumulate in a folder nobody opens, and the knowledge in them is invisible to search.…≈ $0.29 per audio hour on the $24 packCut short-form clips out of a webinar automaticallyThe clips worth posting are buried somewhere in a 60-minute recording and finding them by scrubbing costs more than the…60-min webinar ≈ $0.48

Wire it into Amazon S3 n8n Make.com Google Drive Zapier Slack

Features

Speaker diarization	No
Word-level timestamps	Yes
Streaming / real-time	No
Languages supported	99
HIPAA eligible	No

OpenAI Whisper API vs Whipscribe

Feature	OpenAI Whisper API	Whipscribe
Category	Transcription APIs	Transcription APIs
Pricing	Not verified	$4–$24 one-time packs (credits never expire) · free preview of the opening minutes
Speaker identification	Not verified	Named in the summary, key quotes and chapters
Word timestamps	Not verified	Yes
Streaming	Not verified	No
Languages	99	99
Platforms	API	Web, API, MCP

Alternatives to OpenAI Whisper API

AssemblyAI

Universal-2 model + diarization, PII redaction, topic detection, summarization.

from $0.37/hr

Deepgram

Nova-2 model, excellent streaming, strong at conversational audio.

from $0.0043/min

Rev.ai

The API spin-off of Rev — strong English accuracy, topic detection, custom vocab.

from $0.02/min

Frequently asked about OpenAI Whisper API

Is the OpenAI Whisper API being shut down?

whisper-1 is. OpenAI's deprecations page (checked 26 Oct 2026) lists its removal from the API on 26 Feb 2027, announced on 26 Aug 2026, with gpt-transcribe or gpt-live-transcribe as replacements.

How much does the Whisper API cost?

$0.006 a minute for whisper-1, so $0.36 an hour. gpt-transcribe, the recommended replacement, is $0.0045 a minute and gpt-4o-mini-transcribe $0.003, per OpenAI's pricing page on 26 Oct 2026.

What is the Whisper API file size limit?

25 MB per upload, in mp3, mp4, mpeg, mpga, m4a, wav or webm. Compress or split longer recordings.

Does the OpenAI transcription API identify speakers?

Only gpt-4o-transcribe-diarize, which returns diarized_json with a speaker, start and end on each segment. It is deprecated along with the others for 26 Feb 2027.

What platforms does OpenAI Whisper API support?

OpenAI Whisper API is an API — you call it from whatever you build, on any platform with an HTTP client.

How do I get started with OpenAI Whisper API?

OpenAI Whisper API is used through its API: get a key from the vendor, then call it from your own code. There is no desktop app to install.

How many languages does OpenAI Whisper API support?

OpenAI Whisper API lists 99 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.

What are the limitations of OpenAI Whisper API?

25 MB per upload; whisper-1 and the gpt-4o transcribe models are removed on 26 Feb 2027; speaker labels only through gpt-4o-transcribe-diarize; upload time dominates on large files.

Who is OpenAI Whisper API best for?

Teams already on OpenAI's stack who want Whisper without operating a GPU.

What should I know before choosing OpenAI Whisper API?

Uploads stop at 25 MB in mp3, mp4, mpeg, mpga, m4a, wav or webm. The guide documents word-level timestamps (timestamp_granularities[]) for whisper-1 only, and speaker segments only through gpt-4o-transcribe-diarize. Checked 26 Oct 2026 on OpenAI's own docs.

Is OpenAI Whisper API open source?

No. OpenAI Whisper API is a proprietary API. If you need source you can read and run yourself, the open-source tools in this directory are the place to look.

What kind of tool is OpenAI Whisper API?

In this directory OpenAI Whisper API is filed under commercial api as a API.

What are the alternatives to OpenAI Whisper API?

There is a side-by-side page at /tools/openai-whisper-api-alternatives comparing OpenAI Whisper API with the closest tools in the same category on price, platform and features.

Are there setup recipes for OpenAI Whisper API?

Yes — this page carries 3 tested setups: Python SDK · openai-python v2.x; Node SDK · openai-node v4+; cURL · multipart/form-data.

How is Whipscribe different from OpenAI Whisper API?

OpenAI Whisper API is another vendor's product; Whipscribe is a per-minute transcription service. Recordings are transcribed on our own servers and never used for training, and every job returns five formats plus an AI summary, quotes and topics. Every recording starts with a free preview of its opening minutes, and a pack from $4 (500 minutes) transcribes the rest and opens every export.

Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

What we measured, last 30 days

2,547 recordings, 1,244 audio hours, 66 languages detected. An hour of audio came back in 3.5 minutes for half of the recordings and within 18.0 minutes for nine in ten, measured from the moment the file landed to the finished transcript. Refreshed 2026-10-07; method on how we test.

Transcribe your recordings

Using OpenAI Whisper API today? Send your next recording here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step

Explore

All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing

Whisper's own translate task writes English text only; to keep the original transcript and get English subtitles on the same timestamps, see translate Hindi audio to English.
The API price per minute next to ours, with the arithmetic: transcription API pricing per minute.
Want segments and word times without writing the client? Audio to JSON.

Long recording to get through?

One file up to 10 hours, as an upload or a link: see how to transcribe an MP3 of any length, how to transcribe a podcast and an SRT subtitle file from any recording.

Looking at paid options?

Before you choose a transcription tool or service: see transcription services from $4.