OpenAI Realtime API vs OpenAI Whisper Transcription

Comparing the features of OpenAI Realtime API to OpenAI Whisper Transcription

Feature
OpenAI Realtime API
OpenAI Whisper Transcription

Capability Features

Audio Transcription
Audio Upload
Browser-Based Partitioning
Demo Mode
Enterprise Privacy Commitment
Expanded Model Support Planned
Five New Voices
5
Function Calling
Human and Automated Safety Monitoring
Interruption Handling
No Training on Data Without Permission
One-Click Transcription
Playground Access
Prompt Caching Planned
Public Beta
Reference Client Available
Six Preset Voices
6
Speech-to-Speech
Streaming Audio Inputs/Outputs
Supports Text and Audio Inputs
TextAudio
Ultra Low Latency
WebSocket Connection

Integration Features

Agora Integration
Chat Completions API Integration
LiveKit Integration
OpenAI Node.js SDK Planned
OpenAI Python SDK Planned
OpenAI Whisper Integration
Supported Audio Types
mp3mp4mpegmpgam4awavwebm
Supports GPT-4o
gpt-4o-realtime-preview
Twilio Voice API Integration

Limitation Features

AI Disclosure Requirement
Audio Only Modality (Initially)
Lower Session Limits Tiers 1-4
Lower than 100
No Built-in Whisper
No Mention of Price Plans
No Simultaneous Session Limit Anymore
Requires OpenAI API Key
Simultaneous Sessions Limit Tier 5
100
Usage Policy Restriction

Pricing Features

Approximate Audio Input Price
$0.06/minute
Approximate Audio Output Price
$0.24/minute
Free Trial/Demo
No Free Tier
Pricing Audio Input
$100/1M tokens
Pricing Audio Output
$200/1M tokens
Pricing Cached Audio Input
$20/1M tokens
Pricing Cached Text Input
$2.50/1M tokens
Pricing Text Input
$5/1M tokens
Pricing Text Output
$20/1M tokens