Whisper
whisper-replicateOpenAI's Whisper running on Replicate. General-purpose speech recognition trained on 680k hours of multilingual audio. Transcribes and translates 99 languages, robust to accents and background noise, and outputs plain text, segments, or word-level timestamps.
- Price
- ≈ US$0.0034/run
- Input → output
- Audio → Text
- Developer
- OpenAI
- Updated
- 23 September 2026
Playground
Try Whisper
Input & output
This run
about US$0.0034 · 0.34 credits
US$0.0101 (1.01 credits) are reserved at the start; the actual GPU time is billed.
New here?
10 free credits (US$0.10) when you sign up with Google
Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 9 runs of this model.
Examples
Response
the little tales they tell are false the door was barred locked and bolted as well ripe pears are fit for a queen's table a big wet stain was on the round carpet the kite dipped and swayed but stayed aloft the pleasant hours fly by much too soon the room was crowded with a mild wab the room was crowded with a wild mob this strong arm shall shield your honour she blushed when he gave her a white orchid the beetle droned in the hot june sun the beetle droned in the hot june sun
Response
Imagine that this folder is a dimensional plane. Now, assuming that it has no height and no depth, what would this mean? It would mean that it's a one-dimensional world. So if, hypothetically, an organism was living inside of it, it would only be able to move in a linear path forward and backwards, in a straight line. Now, if we go to the second dimension, we have two dimensions. We have width and we have length. So hypothetically, if an organism lived inside of here, then it would be able to move up, down, left, right, and anywhere else in between. And a two-dimensional world is comprised of an infinite series of one-dimensional worlds stacked upon each other. Just as our three-dimensional world, which has depth and length and height, is comprised of an infinite series of two-dimensional worlds. So now that I have stacked many folders upon each other, we have three dimensions. We have depth, we have length, and we have width. Now, what happens if you keep going on from here on out? We would have a four-dimensional world, but what exactly is a fourth dimension? In order to understand this, we need to understand how dimensions are perceived. We live in the three-dimensional world, but despite that, we actually view things to be two-dimensionally. Take a perfect sphere, for example. If you're looking at a sphere, it looks just like a regular two-dimensional circle. The only way that you can tell, it's an actual sphere instead of a circle, is because of the hues of light down.…
Settings
- language
- auto
Response
The little tales they tell are false. The door was barred, locked, and bolted as well. Ripe pears are fit for a queen's table. A big wet stain was on the round carpet. The kite dipped and swayed, but stayed aloft. The pleasant hours fly by much too soon. The room was crowded with a mild wob. The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid. The beetle droned in the hot June sun.
About Whisper
Whisper is a model by OpenAI in the Speech-to-text category. On Railwail, Whisper costs ≈ US$0.0034 per run.
Pricing
| Typical run (≈ 12 s on T4) | US$0.0034 per run |
|---|---|
| GPU time (T4) | US$0.00027 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = US$0.01
Cost calculator
Price calculator
Typical according to the provider: about 12.4 s
Total
US$0.34
34 credits
Per run
US$0.0034 · 0.34 credits
Billed by the actual GPU time; this is an estimate.
API
curl https://railwail.com/api/v1/audio/transcriptions \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-F model='whisper-replicate' \
-F file=@audio.mp3import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["RAILWAIL_API_KEY"],
base_url="https://railwail.com/api/v1",
)
with open("audio.mp3", "rb") as audio:
transcript = client.audio.transcriptions.create(
model="whisper-replicate",
file=audio,
)
print(transcript.text)import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.RAILWAIL_API_KEY,
baseURL: "https://railwail.com/api/v1",
});
const transcript = await client.audio.transcriptions.create({
model: "whisper-replicate",
file: fs.createReadStream("audio.mp3"),
});
console.log(transcript.text);Specifications
- Model ID
whisper-replicate- Developer
- OpenAI
- Category
- Speech-to-text
- Input
- Audio
- Output
- Text
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- 23 September 2026
Input parameters
Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.
audiorequiredURL or upload of the audio file to transcribe
Type: TextDefault: –Allowed values: –modelType: ChoiceDefault:large-v3Allowed values: large-v3, large-v2, medium, small or baselanguageOptional ISO-639-1 language code (e.g. en, de, fr); auto-detected if omitted
Type: TextDefault: –Allowed values: –translateType: Yes/noDefault:falseAllowed values: –temperatureType: NumberDefault:0Allowed values: 0 to 1
Tags
- replicate
- openai
- whisper
- stt
- transcription
- multilingual
- open-weights
Use cases
Frequently asked questions
What is Whisper?
Whisper is a model by OpenAI in the Speech-to-text category. On Railwail you can call it with an API key through the Railwail API.
How much does Whisper cost on Railwail?
On Railwail, Whisper costs ≈ US$0.0034 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
Which settings does Whisper support?
According to its input schema, Whisper knows these parameters: audio, model (large-v3, large-v2, medium, small or base), language, translate and temperature (0 to 1).
How fast is Whisper?
There are not enough measured runs of Whisper on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is Whisper better than Incredibly Fast Whisper?
That depends on the task. Whisper (OpenAI) and Incredibly Fast Whisper (Community) are both models in the Speech-to-text category. The comparison page shows their prices and specifications side by side.
Compare Whisper and Incredibly Fast WhisperHow do I use Whisper through the API?
Create a Railwail API key and send your request with the model ID whisper-replicate. Code examples for curl, Python and JavaScript are in the API section of this page.
Comparable models
All in this category- Incredibly Fast WhisperCommunity
Whisper Large v3 wrapped with Hugging Face Transformers optimizations (batched inference, flash attention) for very high throughput. Transcribes hours of audio in minutes on a single GPU. Maintained by Vaibhav Srivastav. Good when you need bulk transcription fast.
- SeamlessM4TCommunity
Meta's SeamlessM4T multimodal translation model. Takes speech or text input and produces transcription or translation across about 100 languages, including speech-to-text and speech-to-speech. One model covers ASR plus cross-lingual translation without chaining separate systems.
- SeamlessM4T v2 Large (Speech)Community
Meta SeamlessM4T v2 Large speech mode. Speech-to-speech, speech-to-text, and text-to-speech translation across 100+ languages in a single unified model.
Use Whisper via the API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.