Today, I’m excited to share that we have three new audio models in the API . We’ve also updated our Agents SDK to support the new models, making it possible to convert any text-based agent into an audio agent with a few lines of code. Speech-to-text You can now use gpt-4o-transcribe and gpt-4o-mini…

New audio models in the API + tools for voice agents

rockettnet March 21, 2025, 12:31am 3

Realtime vision coming soon I hope!

2 Likes

Topic		Replies	Views
Semantic VAD might not be working with transcription mode API	4	448	June 30, 2025
Extracting Transcription Without Using input_audio.input_transcription in OpenAI API API realtime , api-realtime	10	370	March 11, 2025
Announcing GPT-4o in the API! Announcements	130	108996	July 4, 2024
New models and developer products announced at DevDay Announcements announcement	70	17659	February 16, 2024
Realtime API (Advanced Voice Mode) Python Implementation API gpt-4o , advanced-voice , realtime	15	10018	February 9, 2025