Since output speech generation is a little bit too expensive How to decrease cost spend in Openai Realtime Console demo? , can I use just audio input API to recognize speech in streaming mode? Any docs or sample of such usage?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to decrease cost spend in Openai Realtime Console demo? | 0 | 64 | December 10, 2024 | |
| How to get text only output from the Realtime API? | 13 | 1510 | January 1, 2025 | |
| Realtime API re-consuming it's own output audio as input audio | 10 | 417 | January 10, 2025 | |
| Is there a way to prevent gpt-4o-audio-preview from returning audio? | 8 | 300 | December 17, 2024 | |
| Realtime: Calling 3rd party API | 0 | 117 | October 7, 2024 |