whisper-1

Common Name: Whisper

OpenAI
Released on Feb 17 12:00 AM
Compare

General-purpose speech recognition model. Transcribes and translates audio to text in multiple languages.

Specifications

Context
128K
Inputaudio
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Pricing

Input Audio$0.01/Minutes

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

$0.17/$0.66/M
ctx128Kmax16Kavailtps
InOutCap

A cost-efficient audio-capable model that accepts text, audio, and image inputs and can generate text and audio outputs.

$0.17/$0.66/M
ctx128Kmax16Kavailtps
InOutCap

A cost-efficient audio-capable model that accepts text, audio, and image inputs and can generate text and audio outputs.

$2.75/$11.00/M
ctx128Kmax16Kavailtps
InOutCap

GPT-4o with native audio input and output capabilities for real-time speech-to-speech conversations.

$2.75/$11.00/M
ctx128Kmax16Kavailtps
InOutCap

GPT-4o with native audio input and output capabilities for real-time speech-to-speech conversations.