{ "checks": { "no_errors": true, "both_inputs_recognized": true, "both_replies_generated": true, "first_playback_before_eof": true, "playback_cancelled": true, "second_turn_completed": true, "second_tail_completed": true, "cancel_before_network_eof": true, "local_model_ran": true, "capture_completed": true, "audio_and_video_tracks": true, "recording_track_durations_match": true }, "passed": true, "dialogue": { "engine": "DH_live mini 2.0", "ua": "Mozilla/5.0 (iPhone; CPU iPhone OS 18_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.0 Mobile/15E148 Safari/604.1", "input": "prerecorded questions played on phone; real STT+LLM+Fish response", "turns": [ { "number": 1, "requestStart": 17784, "receivedSamples": 84640, "playedChunks": 3, "eof": false, "cancelled": true, "transcript": "I have to tell you something. Something really sad just happened to me today.", "reply": "I am so sorry to hear that you are going through such a hard time. Please tell me what happened, because I am right here and ready to listen.", "audioEvents": [ { "startMs": 4044, "durationMs": 500, "setAudioMs": 3, "eof": false }, { "startMs": 4545, "durationMs": 500, "setAudioMs": 1, "eof": false }, { "startMs": 5046.000000000004, "durationMs": 500, "setAudioMs": 1.000000000003638, "eof": false } ], "headersMs": 2791, "firstAudioMs": 3860.0000000000036, "firstPlaybackMs": 4044, "firstPlaybackBeforeEof": true, "callsAtPlayback": 317, "eofAtCancel": false, "cancelMs": 5244.000000000004, "chunksAtCancel": 3, "finishedMs": 5292, "modelCalls": 30, "chunksAfterWait": 3 }, { "number": 2, "requestStart": 27662, "receivedSamples": 72770, "playedChunks": 10, "eof": true, "cancelled": false, "transcript": "Okay, now please cheer me up. Tell me a joke and make me laugh out loud.", "reply": "Why did the scarecrow win an award? Because he was outstanding in his field!", "audioEvents": [ { "startMs": 2570, "durationMs": 500, "setAudioMs": 1, "eof": false }, { "startMs": 3082, "durationMs": 500, "setAudioMs": 0.999999999996362, "eof": false }, { "startMs": 3583, "durationMs": 500, "setAudioMs": 0, "eof": true }, { "startMs": 4086, "durationMs": 500, "setAudioMs": 1.999999999996362, "eof": true }, { "startMs": 4597, "durationMs": 500, "setAudioMs": 0.999999999996362, "eof": true }, { "startMs": 5097.999999999996, "durationMs": 500, "setAudioMs": 0.999999999996362, "eof": true }, { "startMs": 5600, "durationMs": 500, "setAudioMs": 1, "eof": true }, { "startMs": 6108, "durationMs": 500, "setAudioMs": 0, "eof": true }, { "startMs": 6610, "durationMs": 500, "setAudioMs": 1, "eof": true }, { "startMs": 7112, "durationMs": 48.125, "setAudioMs": 1, "eof": true } ], "headersMs": 1300, "firstAudioMs": 2398.0000000000036, "firstPlaybackMs": 2570, "firstPlaybackBeforeEof": true, "callsAtPlayback": 347, "eofMs": 3321, "serverTimings": { "mode": "pooled", "container_age_ms": 14335.444308999999, "stt_start_ms": 75.22486700000286, "stt_end_ms": 1024.725214, "llm_start_ms": 1024.9162019999999, "llm_first_text_ms": 1666.5608500000033, "llm_end_ms": 1693.051778000001, "fish_first_audio_ms": 2130.688335000002, "audio_end_ms": 3021.558524000003 }, "finishedMs": 7197, "modelCalls": 116, "chunksAfterWait": 10 } ], "errors": [], "started": 7698, "finished": 35861.00000000001 }, "recording": { "streams": [ { "index": 0, "codec_name": "h264", "codec_long_name": "H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10", "profile": "Baseline", "codec_type": "video", "codec_tag_string": "avc1", "codec_tag": "0x31637661", "width": 832, "height": 480, "coded_width": 832, "coded_height": 480, "closed_captions": 0, "film_grain": 0, "has_b_frames": 0, "pix_fmt": "yuv420p", "level": 31, "field_order": "progressive", "refs": 1, "is_avc": "true", "nal_length_size": "4", "id": "0x1", "r_frame_rate": "600/1", "avg_frame_rate": "306600/13081", "time_base": "1/600", "start_pts": 26, "start_time": "0.043333", "duration_ts": 13107, "duration": "21.845000", "bit_rate": "9708307", "bits_per_raw_sample": "8", "extradata_size": 24, "disposition": { "default": 1, "dub": 0, "original": 0, "comment": 0, "lyrics": 0, "karaoke": 0, "forced": 0, "hearing_impaired": 0, "visual_impaired": 0, "clean_effects": 0, "attached_pic": 0, "timed_thumbnails": 0, "non_diegetic": 0, "captions": 0, "descriptions": 0, "metadata": 0, "dependent": 0, "still_image": 0 }, "tags": { "creation_time": "2026-10-21T21:15:04.000000Z", "language": "und", "handler_name": "Core Media Video", "vendor_id": "[0][0][0][0]" } }, { "index": 1, "codec_name": "aac", "codec_long_name": "AAC (Advanced Audio Coding)", "profile": "LC", "codec_type": "audio", "codec_tag_string": "mp4a", "codec_tag": "0x6134706d", "sample_fmt": "fltp", "sample_rate": "48000", "channels": 2, "channel_layout": "stereo", "bits_per_sample": 0, "initial_padding": 0, "id": "0x2", "r_frame_rate": "0/0", "avg_frame_rate": "0/0", "time_base": "1/48000", "start_pts": 0, "start_time": "0.000000", "duration_ts": 1052672, "duration": "21.930667", "bit_rate": "86304", "extradata_size": 2, "disposition": { "default": 1, "dub": 0, "original": 0, "comment": 0, "lyrics": 0, "karaoke": 0, "forced": 0, "hearing_impaired": 0, "visual_impaired": 0, "clean_effects": 0, "attached_pic": 0, "timed_thumbnails": 0, "non_diegetic": 0, "captions": 0, "descriptions": 0, "metadata": 0, "dependent": 0, "still_image": 0 }, "tags": { "creation_time": "2026-10-21T21:15:04.000000Z", "language": "und", "handler_name": "Core Media Audio", "vendor_id": "[0][0][0][0]" } } ], "format": { "filename": "/home/tony/work/modal-research-nanoavatar-20261021/experiments/nanoavatar-20261021/driver/ios-dialogue-recording.mp4", "nb_streams": 2, "nb_programs": 0, "nb_stream_groups": 0, "format_name": "mov,mp4,m4a,3gp,3g2,mj2", "format_long_name": "QuickTime / MOV", "start_time": "0.000000", "duration": "21.930667", "size": "26765464", "bit_rate": "9763666", "probe_score": 100, "tags": { "major_brand": "iso5", "minor_version": "1", "compatible_brands": "isomiso5hlsf", "creation_time": "2026-10-21T21:15:04.000000Z" } } }, "limitations": [ "Input is prerecorded question audio, STT begins after input ends", "Speech response is actual network streamed LLM/Fish, adapted to 500ms WAV chunks", "Cancellation may occur after network EOF; eofAtCancel explicitly reported", "Recorded page canvas and WebAudio, not system speaker or microphone", "Mouth quality not accepted; oversized mouth issue unresolved" ] }