AI Models with Audio Input Support
This page lists Large Language Models that offer Audio Input. Compare models, see how they implement this feature, and find the best option for projects requiring robust Audio Input.
Providers
OpenAI
Models with this Capability
GPT-4o mini Realtime
OpenAI · GPT-4o
ID: gpt-4o-mini-realtime
preview
Input
128K tokens
Output
4.1K tokens
Input Cost
$0.60/1M
Output Cost
$2.40/1M
Exceptional at:
realtime processing
audio input
+1
GPT-4o Audio Preview
OpenAI · GPT-4o
ID: gpt-4o-audio-preview-2024-10-01
outdated
Input
0 tokens
Output
0 tokens
Input Cost
$40.00/1M
Output Cost
$80.00/1M
Exceptional at:
audio input processing
audio output generation
+1
GPT-4o Audio Preview
OpenAI · GPT-4o
ID: gpt-4o-audio-preview-2024-12-17
preview
Input
0 tokens
Output
0 tokens
Input Cost
$40.00/1M
Output Cost
$80.00/1M
Exceptional at:
realtime audio processing
realtime text processing
GPT-4o mini Realtime
OpenAI · GPT-4o
ID: gpt-4o-mini-realtime-preview-2024-12-17
preview
Input
128K tokens
Output
4.1K tokens
Input Cost
$0.60/1M
Output Cost
$2.40/1M
Exceptional at:
realtime processing
audio input
+1