Back to whisper
OpenAI /

Whisper Large v3 Turbo
Whisper Large v3 Turbo

Open WeightsMultimodalaudiotextUpdated October 1, 2024
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Whisper Large v3 Turbo

📌 Model Overview

Speech transcription model for accurate audio-to-text and captioning workflows

Whisper Large v3 Turbo is a Open Weights model developed by OpenAI, released on 2024-10-01. It is designed primarily for Multimodal General workloads. Featuring a 448 tokens context window and Undisclosed parameter count, it offers robust performance for enterprise integration, developers, and researchers.


✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window448 tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Multimodal General
Deploymentself-hostable, api-only
Modalityaudio, text
Max OutputMax Output: 448 tokens

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabOpenAI
Release Date2024-10-01
Model TypeOpen Weights
ParametersUndisclosed
Context Window448 tokens
Licenseproprietary
Model Familywhisper

💰 Pricing

Specification Table
Tier / UnitRate (USD)
1M input tokens$0.0023
1M output tokens$0.0023

📜 License & Usage

This model is governed by the proprietary license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 448 tokens

Feature 01

You might also want to compare

Verified Sources

Tags

open-weights

Model Specs

open-weights

Parameters

Undisclosed

Context Window

448 tokens

License

proprietary

Deployment

self-hostableapi-only

Pricing

  • 1M input tokens$0.0023
  • 1M output tokens$0.0023

as of 2026-07-26

Lineage

Model Family

Part of the whisper family

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model