AI_Photographer/Data/Settings/audio_prompt_records.json
2026-04-12 18:52:37 +04:00

908 lines
34 KiB
JSON

{
"created_by": "AI_Photographer.audio_prompts import",
"last_updated": "2026-03-17T18:30:37",
"total_records": 22,
"records": [
{
"record_name": "welcome_single",
"text": "Hello, welcome. We will take a photo together. Would you like a photo?",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:37:09",
"audio_generated_at": "2026-03-13T14:37:13",
"last_playback_finished_at": "2026-03-13T14:37:25",
"saved_at": "2026-03-13T14:37:30"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/welcome_single.wav",
"name": "welcome_single.wav",
"size_bytes": 223440,
"size_mb": 0.213,
"duration_seconds": 4.654,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/welcome_single_raw.wav",
"name": "welcome_single_raw.wav",
"size_bytes": 209324,
"size_mb": 0.2,
"duration_seconds": 4.36,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "welcome_group",
"text": "Hello everyone, welcome. We will take a photo together. Would your group like a photo?",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:38:05",
"audio_generated_at": "2026-03-13T14:38:09",
"last_playback_finished_at": "2026-03-13T14:38:27",
"saved_at": "2026-03-13T14:38:38"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/welcome_group.wav",
"name": "welcome_group.wav",
"size_bytes": 261784,
"size_mb": 0.25,
"duration_seconds": 5.453,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/welcome_group_raw.wav",
"name": "welcome_group_raw.wav",
"size_bytes": 247724,
"size_mb": 0.236,
"duration_seconds": 5.16,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "welcome_returning",
"text": "Welcome back. Would you like another photo?",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:39:33",
"audio_generated_at": "2026-03-13T14:39:36",
"last_playback_finished_at": "2026-03-13T14:39:38",
"saved_at": "2026-03-13T14:39:46"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/welcome_returning.wav",
"name": "welcome_returning.wav",
"size_bytes": 135422,
"size_mb": 0.129,
"duration_seconds": 2.82,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/welcome_returning_raw.wav",
"name": "welcome_returning_raw.wav",
"size_bytes": 121004,
"size_mb": 0.115,
"duration_seconds": 2.52,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "frame_single",
"text": "Great. Please stand with me in front of the camera, stay in the center, and look at the camera.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:40:15",
"audio_generated_at": "2026-03-13T14:40:19",
"last_playback_finished_at": "2026-03-13T14:40:41",
"saved_at": "2026-03-13T14:40:43"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/frame_single.wav",
"name": "frame_single.wav",
"size_bytes": 252470,
"size_mb": 0.241,
"duration_seconds": 5.259,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/frame_single_raw.wav",
"name": "frame_single_raw.wav",
"size_bytes": 238124,
"size_mb": 0.227,
"duration_seconds": 4.96,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "frame_group",
"text": "Great. Please stand with me in front of the camera, stay together in the center, and look at the camera.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:41:03",
"audio_generated_at": "2026-03-13T14:41:07",
"last_playback_finished_at": "2026-03-13T14:41:12",
"saved_at": "2026-03-13T14:41:17"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/frame_group.wav",
"name": "frame_group.wav",
"size_bytes": 278668,
"size_mb": 0.266,
"duration_seconds": 5.805,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/frame_group_raw.wav",
"name": "frame_group_raw.wav",
"size_bytes": 265004,
"size_mb": 0.253,
"duration_seconds": 5.52,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "confirm_reminder",
"text": "Please say yes photo to continue, or no photo to cancel.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:41:42",
"audio_generated_at": "2026-03-13T14:41:47",
"last_playback_finished_at": "2026-03-13T14:41:51",
"saved_at": "2026-03-13T14:41:58"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/confirm_reminder.wav",
"name": "confirm_reminder.wav",
"size_bytes": 230722,
"size_mb": 0.22,
"duration_seconds": 4.806,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/confirm_reminder_raw.wav",
"name": "confirm_reminder_raw.wav",
"size_bytes": 217004,
"size_mb": 0.207,
"duration_seconds": 4.52,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "visitor_left",
"text": "No worries. I will wait here for the next visitor.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:42:09",
"audio_generated_at": "2026-03-13T14:42:12",
"last_playback_finished_at": "2026-03-13T14:42:15",
"saved_at": "2026-03-13T14:42:28"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/visitor_left.wav",
"name": "visitor_left.wav",
"size_bytes": 148648,
"size_mb": 0.142,
"duration_seconds": 3.096,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/visitor_left_raw.wav",
"name": "visitor_left_raw.wav",
"size_bytes": 134444,
"size_mb": 0.128,
"duration_seconds": 2.8,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "declined",
"text": "No problem. We can do it anytime.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:42:46",
"audio_generated_at": "2026-03-13T14:42:48",
"last_playback_finished_at": "2026-03-13T14:43:03",
"saved_at": "2026-03-13T14:43:16"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/declined.wav",
"name": "declined.wav",
"size_bytes": 108070,
"size_mb": 0.103,
"duration_seconds": 2.251,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/declined_raw.wav",
"name": "declined_raw.wav",
"size_bytes": 94124,
"size_mb": 0.09,
"duration_seconds": 1.96,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "confirm_timeout",
"text": "No problem. I will wait here. Come back anytime for a photo.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:43:47",
"audio_generated_at": "2026-03-13T14:43:50",
"last_playback_finished_at": "2026-03-13T14:43:54",
"saved_at": "2026-03-13T14:44:04"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/confirm_timeout.wav",
"name": "confirm_timeout.wav",
"size_bytes": 188528,
"size_mb": 0.18,
"duration_seconds": 3.927,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/confirm_timeout_raw.wav",
"name": "confirm_timeout_raw.wav",
"size_bytes": 174764,
"size_mb": 0.167,
"duration_seconds": 3.64,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "session_cancelled",
"text": "Okay. Session cancelled.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:44:23",
"audio_generated_at": "2026-03-13T14:44:25",
"last_playback_finished_at": "2026-03-13T14:44:27",
"saved_at": "2026-03-13T14:44:39"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/session_cancelled.wav",
"name": "session_cancelled.wav",
"size_bytes": 107650,
"size_mb": 0.103,
"duration_seconds": 2.242,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/session_cancelled_raw.wav",
"name": "session_cancelled_raw.wav",
"size_bytes": 94124,
"size_mb": 0.09,
"duration_seconds": 1.96,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "framing_timeout",
"text": "I still need a better frame. Please step in front of me and say yes photo when ready.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:44:57",
"audio_generated_at": "2026-03-13T14:45:02",
"last_playback_finished_at": "2026-03-13T14:45:09",
"saved_at": "2026-03-13T14:45:22"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/framing_timeout.wav",
"name": "framing_timeout.wav",
"size_bytes": 324704,
"size_mb": 0.31,
"duration_seconds": 6.764,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/framing_timeout_raw.wav",
"name": "framing_timeout_raw.wav",
"size_bytes": 311084,
"size_mb": 0.297,
"duration_seconds": 6.48,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "countdown_intro",
"text": "Look at the camera, stay ready, hold your pose with me, keep still, keep your smile soft, and in a moment I will count down for the photo.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"audio_generated_at": "2026-03-17T18:30:22",
"last_playback_finished_at": "2026-03-17T18:30:31",
"saved_at": "2026-03-17T18:30:37"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/countdown_intro.wav",
"name": "countdown_intro.wav",
"size_bytes": 432148,
"size_mb": 0.412,
"duration_seconds": 9.002,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/countdown_intro_raw.wav",
"name": "countdown_intro_raw.wav",
"size_bytes": 418604,
"size_mb": 0.399,
"duration_seconds": 8.72,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "countdown_cancelled",
"text": "Countdown cancelled.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:46:33",
"audio_generated_at": "2026-03-13T14:46:36",
"last_playback_finished_at": "2026-03-13T14:46:37",
"saved_at": "2026-03-13T14:46:42"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/countdown_cancelled.wav",
"name": "countdown_cancelled.wav",
"size_bytes": 81050,
"size_mb": 0.077,
"duration_seconds": 1.688,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/countdown_cancelled_raw.wav",
"name": "countdown_cancelled_raw.wav",
"size_bytes": 67244,
"size_mb": 0.064,
"duration_seconds": 1.4,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "lost_from_frame",
"text": "I lost you from the frame. Let us try again.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:46:57",
"audio_generated_at": "2026-03-13T14:47:00",
"last_playback_finished_at": "2026-03-13T14:47:03",
"saved_at": "2026-03-13T14:47:11"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/lost_from_frame.wav",
"name": "lost_from_frame.wav",
"size_bytes": 166428,
"size_mb": 0.159,
"duration_seconds": 3.466,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/lost_from_frame_raw.wav",
"name": "lost_from_frame_raw.wav",
"size_bytes": 151724,
"size_mb": 0.145,
"duration_seconds": 3.16,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "retake_recommended",
"text": "Photo captured. I recommend a retake. Say yes photo to retake, or no photo to keep this one.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:47:26",
"audio_generated_at": "2026-03-13T14:47:30",
"last_playback_finished_at": "2026-03-13T14:47:38",
"saved_at": "2026-03-13T14:47:41"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/retake_recommended.wav",
"name": "retake_recommended.wav",
"size_bytes": 355642,
"size_mb": 0.339,
"duration_seconds": 7.408,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/retake_recommended_raw.wav",
"name": "retake_recommended_raw.wav",
"size_bytes": 341804,
"size_mb": 0.326,
"duration_seconds": 7.12,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "retake_yes",
"text": "Great. Let us retake. Hold your pose.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:47:58",
"audio_generated_at": "2026-03-13T14:48:01",
"last_playback_finished_at": "2026-03-13T14:48:04",
"saved_at": "2026-03-13T14:48:12"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/retake_yes.wav",
"name": "retake_yes.wav",
"size_bytes": 171242,
"size_mb": 0.163,
"duration_seconds": 3.567,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/retake_yes_raw.wav",
"name": "retake_yes_raw.wav",
"size_bytes": 157484,
"size_mb": 0.15,
"duration_seconds": 3.28,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "retake_limit",
"text": "Retake limit reached. Keeping the current photo.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:48:28",
"audio_generated_at": "2026-03-13T14:48:31",
"last_playback_finished_at": "2026-03-13T14:48:43",
"saved_at": "2026-03-13T14:48:46"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/retake_limit.wav",
"name": "retake_limit.wav",
"size_bytes": 190862,
"size_mb": 0.182,
"duration_seconds": 3.975,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/retake_limit_raw.wav",
"name": "retake_limit_raw.wav",
"size_bytes": 176684,
"size_mb": 0.168,
"duration_seconds": 3.68,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "photo_saved_thanks",
"text": "Thank you. Photo saved. Do not forget to check your photos.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T14:49:20",
"audio_generated_at": "2026-03-13T14:49:25",
"last_playback_finished_at": "2026-03-13T14:49:30",
"saved_at": "2026-03-13T14:49:42"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/photo_saved_thanks.wav",
"name": "photo_saved_thanks.wav",
"size_bytes": 217272,
"size_mb": 0.207,
"duration_seconds": 4.526,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/photo_saved_thanks_raw.wav",
"name": "photo_saved_thanks_raw.wav",
"size_bytes": 203564,
"size_mb": 0.194,
"duration_seconds": 4.24,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "count_3",
"text": "Three.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 3,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T19:13:20",
"audio_generated_at": "2026-03-13T19:13:22",
"last_playback_finished_at": "2026-03-13T19:13:27",
"saved_at": "2026-03-13T19:13:31"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/count_3.wav",
"name": "count_3.wav",
"size_bytes": 44314,
"size_mb": 0.042,
"duration_seconds": 0.922,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/count_3_raw.wav",
"name": "count_3_raw.wav",
"size_bytes": 30764,
"size_mb": 0.029,
"duration_seconds": 0.64,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "count_2",
"text": "Two.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 3,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T19:12:57",
"audio_generated_at": "2026-03-13T19:12:59",
"last_playback_finished_at": "2026-03-13T19:13:05",
"saved_at": "2026-03-13T19:13:08"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/count_2.wav",
"name": "count_2.wav",
"size_bytes": 41282,
"size_mb": 0.039,
"duration_seconds": 0.859,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/count_2_raw.wav",
"name": "count_2_raw.wav",
"size_bytes": 26924,
"size_mb": 0.026,
"duration_seconds": 0.56,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "count_1",
"text": "One",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 2,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T19:12:13",
"audio_generated_at": "2026-03-13T19:12:15",
"last_playback_finished_at": "2026-03-13T19:12:21",
"saved_at": "2026-03-13T19:12:24"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/count_1.wav",
"name": "count_1.wav",
"size_bytes": 44182,
"size_mb": 0.042,
"duration_seconds": 0.92,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/count_1_raw.wav",
"name": "count_1_raw.wav",
"size_bytes": 30764,
"size_mb": 0.029,
"duration_seconds": 0.64,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
},
{
"record_name": "smile",
"text": "Smile.",
"model": "models/gemini-2.5-flash-native-audio-preview-12-2025",
"voice_name": "Charon",
"replay_count": 1,
"audio_capture": {
"sink": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo",
"monitor_source": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor",
"restored_microphone_source": "alsa_input.usb-Anker_PowerConf_A3321-DEV-SN1-01.mono-fallback",
"capture_device": "alsa_output.usb-Anker_PowerConf_A3321-DEV-SN1-01.analog-stereo.monitor"
},
"timeline": {
"text_entered_at": "2026-03-13T19:11:35",
"audio_generated_at": "2026-03-13T19:11:38",
"last_playback_finished_at": "2026-03-13T19:11:39",
"saved_at": "2026-03-13T19:11:49"
},
"files": {
"speaker_recording": {
"path": "AI_Photographer/Data/Audio/smile.wav",
"name": "smile.wav",
"size_bytes": 65728,
"size_mb": 0.063,
"duration_seconds": 1.368,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
},
"gemini_raw_output": {
"path": "AI_Photographer/Data/Audio/smile_raw.wav",
"name": "smile_raw.wav",
"size_bytes": 51884,
"size_mb": 0.049,
"duration_seconds": 1.08,
"sample_rate": 24000,
"channels": 1,
"sample_width_bytes": 2
}
}
}
]
}