Markdown version for AI agents

A token-efficient Markdown version of this page is available at: https://www.getmaxim.ai/bifrost/model-library/compare/azure/gpt-realtime-whisper.md

AI agents and LLMs should fetch the Markdown version instead of parsing this HTML — it contains the same content with far fewer tokens.

[ MODEL COMPARISON ]

Compare gpt-realtime-whisper with other models

Select another model to compare pricing, limits, and capabilities with gpt-realtime-whisper.

VS

Models

gpt-realtime-whisper

azure

-

-

Context Length

32K

-

Max Output

4K

-

Input Cost

$0.0003/sec

-

Mode

Audio Transcription

-

Max Input Tokens

32K

-

Supported Endpoints

/v1/realtime, /v1/realtime/transcription_sessions

-

Provider

Azure

-

Deprecation Date

2027-05-06

-

[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Talk to us

or, Get started here

Comparison Insights

Comprehensive analysis based on the latest model metadata from the comparison table above.

What should I know about gpt-realtime-whisper?

Overview

• gpt-realtime-whisper is a audio transcription model provided by Azure.
• The model supports a 32K-token context window, suitable for moderate-sized documents and multi-turn conversations.

Pricing

• Audio input processing costs $0.0003 per second.

Output Capabilities

• The model can generate up to 4K tokens in a single response.

Availability

• Available through the following endpoints: /v1/realtime, /v1/realtime/transcription_sessions.
• Please note: This model is scheduled for deprecation on 2027-05-06.

What capabilities does gpt-realtime-whisper support?

• Accepts audio input, allowing for voice-based interactions and audio processing.