Whisper Large v3 Turbo API.
Make speech searchable.

Whisper Large v3 Turbo converts speech into text. Use Blade’s hosted transcription route for recordings, voice notes and content workflows without deploying the speech model yourself.

€5 in free credits for every new customer.

Try Whisper Large v3 Turbo

From €0.000155 per audio minute. View the pricing details.

Speech to text
with Whisper Large v3 Turbo.

Practical starting points for Whisper Large v3 Turbo. Choose one task, define the expected output and measure the result on your own examples.

Transcribe voice notes

Turn uploaded notes into text your application can display, edit and store with the original recording.

Prepare caption text

Generate a transcript for a captioning workflow. Confirm timestamp support separately before promising timed subtitles.

Index recorded content

Feed reviewed transcripts into search or retrieval systems. Preserve recording references so users can verify the source.

Explore the speech to text workflow ↗

Whisper Large v3 Turbo pricing

Whisper Large v3 Turbo
API pricing.

These are catalogue “From” rates in EUR. Dynamic pricing can change the applicable price. Confirm your model, request route and active billing unit before estimating a workload.

See Whisper Large v3 Turbo on the rate card ↗

Per audio minute: From€0.000155

A concrete example
60 audio minutes = €0.009300 at the displayed starting rates.

Illustration only; excludes retries, other models and paid tools. Catalogue updated 2026-10-22.

Check current rates ↗

API integration

How to use
the Whisper Large v3 Turbo API.

Use the Blade model ID whisper-large-v3-turbo and keep your API key in your backend environment. Verify account access and supported parameters before connecting production traffic.

Create a Blade API key in the console.
Run pip install openai and set BLADE_API_KEY.
Run a small request and inspect the output before building the rest of your workflow.

Read the API reference ↗

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.models.blade.sh/v1",
    api_key=os.environ["BLADE_API_KEY"],
    timeout=120.0,
)

with open("recording.wav", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        model="whisper-large-v3-turbo",
        file=audio,
    )
print(transcript.text)

Install openai, set BLADE_API_KEY and provide recording.wav. The documented route accepts audio uploads up to 25 MB. This sends a billed request.

Whisper Large v3 Turbo API FAQ.

What can I use Whisper Large v3 Turbo for?

Whisper Large v3 Turbo converts speech into text. Use Blade’s hosted transcription route for recordings, voice notes and content workflows without deploying the speech model yourself. Its Blade model ID is whisper-large-v3-turbo.

How much does Whisper Large v3 Turbo cost on Blade?

Per audio minute: from €0.000155. These are dynamic catalogue starting rates as of 2026-10-22, not fixed prices for every request. Check the console for current rates.

What should I confirm before integrating?

The 30-second segment size listed in the catalogue is a model-processing unit, not necessarily the maximum file duration. The documented upload limit is 25 MB. Speaker diarization and timestamp options are not established by this example.

Model reference: Publisher model reference ↗. Hosted configuration and pricing: Blade catalogue, 2026-10-22.

Choose by task, input type and billing unit. Browse all models ↗
Need to configure your own worker? Read the Whisper Large v3 Turbo GPU deployment guide ↗

Whisper Large v3 Turbo API.Make speech searchable.

Speech to textwith Whisper Large v3 Turbo.