← All Models

Whisper V3

OpenAIOpen Source

OpenAI's open-source automatic speech recognition model. Supports 100+ languages with near-human accuracy for transcription.

Specifications

Context Window

N/A (audio)

Parameters

1.55B

Input Price / 1M tokens

Free

Output Price / 1M tokens

Free

Release Date

November 6, 2023

Open Source

Yes

Best For

Speech-to-texttranscriptiontranslation

Pricing (per 1M tokens)

Input

Free

Output

Free

Compare Whisper V3

Other OpenAI models

GPT-4o
128K#2
GPT-o3
200K#2
GPT-o1
200K#3
GPT-4o Mini
128K#15
DALL-E 3
N/A (image)

Other models

Claude Opus 4Anthropic
#1
Claude Sonnet 4Anthropic
#3
Gemini 2.5 ProGoogle DeepMind
#4
Grok 3xAI
#5
DeepSeek R1DeepSeek
#5
DeepSeek V3DeepSeek
#6

More

Model Benchmarks →All Models →OpenAI Company Profile →

Frequently Asked Questions

What is Whisper V3?▾
OpenAI's open-source automatic speech recognition model. Supports 100+ languages with near-human accuracy for transcription.
How much does Whisper V3 cost?▾
Whisper V3 costs Free per 1M input tokens and Free per 1M output tokens.
What is Whisper V3 best for?▾
Whisper V3 is best for: Speech-to-text, transcription, translation.
Is Whisper V3 open source?▾
Yes, Whisper V3 is open source and can be self-hosted.