Hi everyone, I have been testing “half-cascade” gemini live model and the documentation says it internally generates text as output and make a TTS step. Then, are there any recommendations for the system prompt in order the entire audio-audio pipeline works properly?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to specify a prompt for Gemini Live Voice agent? | 2 | 200 | July 13, 2025 | |
| Prompts for ASR task | 1 | 141 | July 29, 2025 | |
| How to bias input_audio_transcription with a prompt in the Gemini Live API? | 1 | 104 | July 10, 2025 | |
| Speaker Diarized and Timestamped Transcription with Gemini | 3 | 370 | August 19, 2025 | |
| A few prompt engineering questions | 4 | 272 | August 20, 2025 |