dmtanner/parakeet-tdt-0.6b-v3 🔢📝🖼️✓ → 📝

▶️ 1.0K runs 📅 Aug 2025 ⚙️ Cog 0.16.5
speech-to-text video-auto-captioning

About

ASR model, created by Nvidia, with word-level timestamps available. Supports .wav inputs, or m3u8 urls, with a start and end time (to only process a section of the m3u8).

Example Output

Output

{"text": "Are you ready? Of course you're ready. You're a rock star. How's it looking, Barney? We should have about ten minutes. Well, that's perfect. We're only one. All systems go. Yeah, you go. Go. That's nice. Nothing to worry about. There she is. Now you love her. She's your passion. Be tender to her. Be honest. Be tender. Remind her what love is.", "timestamps": {"timestep": [140, 142, 144, 148, 151, 153, 156, 157, 158, 160, 161, 163, 164, 165, 166, 167, 169, 170, 171, 172, 173, 175, 178, 180, 187, 211, 213, 214, 216, 216, 217, 219, 221, 223, 226, 232, 235, 239, 241, 243, 245, 249, 254, 258, 266, 269, 272, 274, 275, 277, 279, 281, 283, 287, 290, 294, 296, 297, 299, 305, 311, 314, 320, 323, 327, 330, 331, 333, 334, 336, 342, 348, 351, 369, 535, 538, 540, 543, 547, 551, 556, 558, 560, 562, 564, 566, 567, 569, 649, 652, 655, 659, 667, 671, 675, 692, 696, 704, 713, 716, 718, 720, 721, 723, 726, 730, 732, 739, 748, 751, 755, 759, 764, 767, 771, 775, 777, 794, 800, 803, 815, 819, 821, 824, 828, 836, 843, 847, 866], "char": [{"char": ["A"], "start_offset": 140, "end_offset": 142, "start": 11.200000000000001, "end": 11.36}, {"char": ["re"], "start_offset": 142, "end_offset": 144, "start": 11.36, "end": 11.52}, {"char": ["you"], "start_offset": 144, "end_offset": 148, "start": 11.52, "end": 11.84}, {"char": ["re"], "start_offset": 148, "end_offset": 151, "start": 11.84, "end": 12.08}, {"char": ["ady"], "start_offset": 151, "end_offset": 153, "start": 12.08, "end": 12.24}, {"char": ["?"], "start_offset": 153, "end_offset": 153, "start": 12.24, "end": 12.24}, {"char": ["O"], "start_offset": 156, "end_offset": 157, "start": 12.48, "end": 12.56}, {"char": ["f"], "start_offset": 157, "end_offset": 158, "start": 12.56, "end": 12.64}, {"char": ["co"], "start_offset": 158, "end_offset": 160, "start": 12.64, "end": 12.8}, {"char": ["ur"], "start_offset": 160, "end_offset": 161, "start": 12.8, "end": 12.88}, {"char": ["se"], "start_offset": 161, "end_offset": 161, "start": 12.88, "end": 12.88}, {"char": ["you"], "start_offset": 163, "end_offset": 164, "start": 13.040000000000001, "end": 13.120000000000001}, {"char": ["'"], "start_offset": 164, "end_offset": 164, "start": 13.120000000000001, "end": 13.120000000000001}, {"char": ["re"], "start_offset": 165, "end_offset": 166, "start": 13.200000000000001, "end": 13.280000000000001}, {"char": ["re"], "start_offset": 166, "end_offset": 167, "start": 13.280000000000001, "end": 13.36}, {"char": ["ady"], "start_offset": 167, "end_offset": 169, "start": 13.36, "end": 13.52}, {"char": ["."], "start_offset": 169, "end_offset": 169, "start": 13.52, "end": 13.52}, {"char": ["You"], "start_offset": 170, "end_offset": 171, "start": 13.6, "end": 13.68}, {"char": ["'"], "start_offset": 171, "end_offset": 171, "start": 13.68, "end": 13.68}, {"char": ["re"], "start_offset": 172, "end_offset": 173, "start": 13.76, "end": 13.84}, {"char": ["a"], "start_offset": 173, "end_offset": 175, "start": 13.84, "end": 14.0}, {"char": ["ro"], "start_offset": 175, "end_offset": 178, "start": 14.0, "end": 14.24}, {"char": ["ck"], "start_offset": 178, "end_offset": 180, "start": 14.24, "end": 14.4}, {"char": ["star"], "start_offset": 180, "end_offset": 184, "start": 14.4, "end": 14.72}, {"char": ["."], "start_offset": 184, "end_offset": 184, "start": 14.72, "end": 14.72}, {"char": ["H"], "start_offset": 211, "end_offset": 213, "start": 16.88, "end": 17.04}, {"char": ["ow"], "start_offset": 213, "end_offset": 214, "start": 17.04, "end": 17.12}, {"char": ["'"], "start_offset": 214, "end_offset": 214, "start": 17.12, "end": 17.12}, {"char": ["s"], "start_offset": 216, "end_offset": 216, "start": 17.28, "end": 17.28}, {"char": ["it"], "start_offset": 216, "end_offset": 217, "start": 17.28, "end": 17.36}, {"char": ["look"], "start_offset": 217, "end_offset": 219, "start": 17.36, "end": 17.52}, {"char": ["ing"], "start_offset": 219, "end_offset": 220, "start": 17.52, "end": 17.6}, {"char": [","], "start_offset": 220, "end_offset": 220, "start": 17.6, "end": 17.6}, {"char": ["Bar"], "start_offset": 223, "end_offset": 226, "start": 17.84, "end": 18.080000000000002}, {"char": ["ney"], "start_offset": 226, "end_offset": 229, "start": 18.080000000000002, "end": 18.32}, {"char": ["?"], "start_offset": 229, "end_offset": 229, "start": 18.32, "end": 18.32}, {"char": ["We"], "start_offset": 235, "end_offset": 239, "start": 18.8, "end": 19.12}, {"char": ["sho"], "start_offset": 239, "end_offset": 241, "start": 19.12, "end": 19.28}, {"char": ["uld"], "start_offset": 241, "end_offset": 243, "start": 19.28, "end": 19.44}, {"char": ["have"], "start_offset": 243, "end_offset": 245, "start": 19.44, "end": 19.6}, {"char": ["about"], "start_offset": 245, "end_offset": 249, "start": 19.6, "end": 19.92}, {"char": ["ten"], "start_offset": 249, "end_offset": 251, "start": 19.92, "end": 20.080000000000002}, {"char": ["minut"], "start_offset": 254, "end_offset": 258, "start": 20.32, "end": 20.64}, {"char": ["es"], "start_offset": 258, "end_offset": 262, "start": 20.64, "end": 20.96}, {"char": ["."], "start_offset": 262, "end_offset": 262, "start": 20.96, "end": 20.96}, {"char": ["W"], "start_offset": 269, "end_offset": 272, "start": 21.52, "end": 21.76}, {"char": ["ell"], "start_offset": 272, "end_offset": 274, "start": 21.76, "end": 21.92}, {"char": [","], "start_offset": 274, "end_offset": 274, "start": 21.92, "end": 21.92}, {"char": ["that"], "start_offset": 275, "end_offset": 277, "start": 22.0, "end": 22.16}, {"char": ["'"], "start_offset": 277, "end_offset": 277, "start": 22.16, "end": 22.16}, {"char": ["s"], "start_offset": 279, "end_offset": 281, "start": 22.32, "end": 22.48}, {"char": ["per"], "start_offset": 281, "end_offset": 283, "start": 22.48, "end": 22.64}, {"char": ["fe"], "start_offset": 283, "end_offset": 287, "start": 22.64, "end": 22.96}, {"char": ["ct"], "start_offset": 287, "end_offset": 290, "start": 22.96, "end": 23.2}, {"char": ["."], "start_offset": 290, "end_offset": 290, "start": 23.2, "end": 23.2}, {"char": ["We"], "start_offset": 294, "end_offset": 296, "start": 23.52, "end": 23.68}, {"char": ["'"], "start_offset": 296, "end_offset": 296, "start": 23.68, "end": 23.68}, {"char": ["re"], "start_offset": 297, "end_offset": 299, "start": 23.76, "end": 23.92}, {"char": ["only"], "start_offset": 299, "end_offset": 301, "start": 23.92, "end": 24.080000000000002}, {"char": ["one"], "start_offset": 305, "end_offset": 309, "start": 24.400000000000002, "end": 24.72}, {"char": ["."], "start_offset": 309, "end_offset": 309, "start": 24.72, "end": 24.72}, {"char": ["All"], "start_offset": 314, "end_offset": 317, "start": 25.12, "end": 25.36}, {"char": ["system"], "start_offset": 320, "end_offset": 323, "start": 25.6, "end": 25.84}, {"char": ["s"], "start_offset": 323, "end_offset": 325, "start": 25.84, "end": 26.0}, {"char": ["go"], "start_offset": 327, "end_offset": 330, "start": 26.16, "end": 26.400000000000002}, {"char": ["."], "start_offset": 330, "end_offset": 330, "start": 26.400000000000002, "end": 26.400000000000002}, {"char": ["Ye"], "start_offset": 331, "end_offset": 333, "start": 26.48, "end": 26.64}, {"char": ["ah"], "start_offset": 333, "end_offset": 334, "start": 26.64, "end": 26.72}, {"char": [","], "start_offset": 334, "end_offset": 334, "start": 26.72, "end": 26.72}, {"char": ["you"], "start_offset": 336, "end_offset": 339, "start": 26.88, "end": 27.12}, {"char": ["go"], "start_offset": 342, "end_offset": 346, "start": 27.36, "end": 27.68}, {"char": ["."], "start_offset": 346, "end_offset": 346, "start": 27.68, "end": 27.68}, {"char": ["Go"], "start_offset": 351, "end_offset": 355, "start": 28.080000000000002, "end": 28.400000000000002}, {"char": ["."], "start_offset": 355, "end_offset": 355, "start": 28.400000000000002, "end": 28.400000000000002}, {"char": ["That"], "start_offset": 535, "end_offset": 538, "start": 42.800000000000004, "end": 43.04}, {"char": ["'"], "start_offset": 538, "end_offset": 538, "start": 43.04, "end": 43.04}, {"char": ["s"], "start_offset": 540, "end_offset": 543, "start": 43.2, "end": 43.44}, {"char": ["n"], "start_offset": 543, "end_offset": 547, "start": 43.44, "end": 43.76}, {"char": ["ice"], "start_offset": 547, "end_offset": 551, "start": 43.76, "end": 44.08}, {"char": ["."], "start_offset": 551, "end_offset": 551, "start": 44.08, "end": 44.08}, {"char": ["N"], "start_offset": 556, "end_offset": 558, "start": 44.480000000000004, "end": 44.64}, {"char": ["ot"], "start_offset": 558, "end_offset": 560, "start": 44.64, "end": 44.800000000000004}, {"char": ["hing"], "start_offset": 560, "end_offset": 562, "start": 44.800000000000004, "end": 44.96}, {"char": ["to"], "start_offset": 562, "end_offset": 564, "start": 44.96, "end": 45.12}, {"char": ["wor"], "start_offset": 564, "end_offset": 566, "start": 45.12, "end": 45.28}, {"char": ["ry"], "start_offset": 566, "end_offset": 567, "start": 45.28, "end": 45.36}, {"char": ["about"], "start_offset": 567, "end_offset": 569, "start": 45.36, "end": 45.52}, {"char": ["."], "start_offset": 569, "end_offset": 569, "start": 45.52, "end": 45.52}, {"char": ["Th"], "start_offset": 649, "end_offset": 652, "start": 51.92, "end": 52.160000000000004}, {"char": ["ere"], "start_offset": 652, "end_offset": 655, "start": 52.160000000000004, "end": 52.4}, {"char": ["she"], "start_offset": 655, "end_offset": 659, "start": 52.4, "end": 52.72}, {"char": ["is"], "start_offset": 659, "end_offset": 663, "start": 52.72, "end": 53.04}, {"char": ["."], "start_offset": 663, "end_offset": 663, "start": 53.04, "end": 53.04}, {"char": ["N"], "start_offset": 671, "end_offset": 675, "start": 53.68, "end": 54.0}, {"char": ["ow"], "start_offset": 675, "end_offset": 679, "start": 54.0, "end": 54.32}, {"char": ["you"], "start_offset": 692, "end_offset": 696, "start": 55.36, "end": 55.68}, {"char": ["love"], "start_offset": 696, "end_offset": 700, "start": 55.68, "end": 56.0}, {"char": ["her"], "start_offset": 704, "end_offset": 708, "start": 56.32, "end": 56.64}, {"char": ["."], "start_offset": 708, "end_offset": 708, "start": 56.64, "end": 56.64}, {"char": ["S"], "start_offset": 716, "end_offset": 718, "start": 57.28, "end": 57.44}, {"char": ["he"], "start_offset": 718, "end_offset": 720, "start": 57.44, "end": 57.6}, {"char": ["'"], "start_offset": 720, "end_offset": 720, "start": 57.6, "end": 57.6}, {"char": ["s"], "start_offset": 721, "end_offset": 723, "start": 57.68, "end": 57.84}, {"char": ["your"], "start_offset": 723, "end_offset": 726, "start": 57.84, "end": 58.08}, {"char": ["pass"], "start_offset": 726, "end_offset": 730, "start": 58.08, "end": 58.4}, {"char": ["ion"], "start_offset": 730, "end_offset": 732, "start": 58.4, "end": 58.56}, {"char": ["."], "start_offset": 732, "end_offset": 732, "start": 58.56, "end": 58.56}, {"char": ["Be"], "start_offset": 739, "end_offset": 743, "start": 59.120000000000005, "end": 59.44}, {"char": ["t"], "start_offset": 748, "end_offset": 751, "start": 59.84, "end": 60.08}, {"char": ["ender"], "start_offset": 751, "end_offset": 753, "start": 60.08, "end": 60.24}, {"char": ["to"], "start_offset": 755, "end_offset": 759, "start": 60.4, "end": 60.72}, {"char": ["her"], "start_offset": 759, "end_offset": 763, "start": 60.72, "end": 61.04}, {"char": ["."], "start_offset": 763, "end_offset": 763, "start": 61.04, "end": 61.04}, {"char": ["Be"], "start_offset": 767, "end_offset": 771, "start": 61.36, "end": 61.68}, {"char": ["hon"], "start_offset": 771, "end_offset": 775, "start": 61.68, "end": 62.0}, {"char": ["est"], "start_offset": 775, "end_offset": 777, "start": 62.0, "end": 62.160000000000004}, {"char": ["."], "start_offset": 777, "end_offset": 777, "start": 62.160000000000004, "end": 62.160000000000004}, {"char": ["Be"], "start_offset": 794, "end_offset": 797, "start": 63.52, "end": 63.76}, {"char": ["t"], "start_offset": 800, "end_offset": 803, "start": 64.0, "end": 64.24}, {"char": ["ender"], "start_offset": 803, "end_offset": 806, "start": 64.24, "end": 64.48}, {"char": ["."], "start_offset": 806, "end_offset": 806, "start": 64.48, "end": 64.48}, {"char": ["R"], "start_offset": 819, "end_offset": 821, "start": 65.52, "end": 65.68}, {"char": ["em"], "start_offset": 821, "end_offset": 824, "start": 65.68, "end": 65.92}, {"char": ["ind"], "start_offset": 824, "end_offset": 828, "start": 65.92, "end": 66.24}, {"char": ["her"], "start_offset": 828, "end_offset": 832, "start": 66.24, "end": 66.56}, {"char": ["what"], "start_offset": 836, "end_offset": 839, "start": 66.88, "end": 67.12}, {"char": ["love"], "start_offset": 843, "end_offset": 847, "start": 67.44, "end": 67.76}, {"char": ["is"], "start_offset": 847, "end_offset": 850, "start": 67.76, "end": 68.0}, {"char": ["."], "start_offset": 850, "end_offset": 850, "start": 68.0, "end": 68.0}], "word": [{"word": "Are", "start_offset": 140, "end_offset": 144, "start": 11.200000000000001, "end": 11.52}, {"word": "you", "start_offset": 144, "end_offset": 148, "start": 11.52, "end": 11.84}, {"word": "ready?", "start_offset": 148, "end_offset": 153, "start": 11.84, "end": 12.24}, {"word": "Of", "start_offset": 156, "end_offset": 158, "start": 12.48, "end": 12.64}, {"word": "course", "start_offset": 158, "end_offset": 161, "start": 12.64, "end": 12.88}, {"word": "you're", "start_offset": 163, "end_offset": 166, "start": 13.040000000000001, "end": 13.280000000000001}, {"word": "ready.", "start_offset": 166, "end_offset": 169, "start": 13.280000000000001, "end": 13.52}, {"word": "You're", "start_offset": 170, "end_offset": 173, "start": 13.6, "end": 13.84}, {"word": "a", "start_offset": 173, "end_offset": 175, "start": 13.84, "end": 14.0}, {"word": "rock", "start_offset": 175, "end_offset": 180, "start": 14.0, "end": 14.4}, {"word": "star.", "start_offset": 180, "end_offset": 184, "start": 14.4, "end": 14.72}, {"word": "How's", "start_offset": 211, "end_offset": 216, "start": 16.88, "end": 17.28}, {"word": "it", "start_offset": 216, "end_offset": 217, "start": 17.28, "end": 17.36}, {"word": "looking,", "start_offset": 217, "end_offset": 220, "start": 17.36, "end": 17.6}, {"word": "Barney?", "start_offset": 223, "end_offset": 229, "start": 17.84, "end": 18.32}, {"word": "We", "start_offset": 235, "end_offset": 239, "start": 18.8, "end": 19.12}, {"word": "should", "start_offset": 239, "end_offset": 243, "start": 19.12, "end": 19.44}, {"word": "have", "start_offset": 243, "end_offset": 245, "start": 19.44, "end": 19.6}, {"word": "about", "start_offset": 245, "end_offset": 249, "start": 19.6, "end": 19.92}, {"word": "ten", "start_offset": 249, "end_offset": 251, "start": 19.92, "end": 20.080000000000002}, {"word": "minutes.", "start_offset": 254, "end_offset": 262, "start": 20.32, "end": 20.96}, {"word": "Well,", "start_offset": 269, "end_offset": 274, "start": 21.52, "end": 21.92}, {"word": "that's", "start_offset": 275, "end_offset": 281, "start": 22.0, "end": 22.48}, {"word": "perfect.", "start_offset": 281, "end_offset": 290, "start": 22.48, "end": 23.2}, {"word": "We're", "start_offset": 294, "end_offset": 299, "start": 23.52, "end": 23.92}, {"word": "only", "start_offset": 299, "end_offset": 301, "start": 23.92, "end": 24.080000000000002}, {"word": "one.", "start_offset": 305, "end_offset": 309, "start": 24.400000000000002, "end": 24.72}, {"word": "All", "start_offset": 314, "end_offset": 317, "start": 25.12, "end": 25.36}, {"word": "systems", "start_offset": 320, "end_offset": 325, "start": 25.6, "end": 26.0}, {"word": "go.", "start_offset": 327, "end_offset": 330, "start": 26.16, "end": 26.400000000000002}, {"word": "Yeah,", "start_offset": 331, "end_offset": 334, "start": 26.48, "end": 26.72}, {"word": "you", "start_offset": 336, "end_offset": 339, "start": 26.88, "end": 27.12}, {"word": "go.", "start_offset": 342, "end_offset": 346, "start": 27.36, "end": 27.68}, {"word": "Go.", "start_offset": 351, "end_offset": 355, "start": 28.080000000000002, "end": 28.400000000000002}, {"word": "That's", "start_offset": 535, "end_offset": 543, "start": 42.800000000000004, "end": 43.44}, {"word": "nice.", "start_offset": 543, "end_offset": 551, "start": 43.44, "end": 44.08}, {"word": "Nothing", "start_offset": 556, "end_offset": 562, "start": 44.480000000000004, "end": 44.96}, {"word": "to", "start_offset": 562, "end_offset": 564, "start": 44.96, "end": 45.12}, {"word": "worry", "start_offset": 564, "end_offset": 567, "start": 45.12, "end": 45.36}, {"word": "about.", "start_offset": 567, "end_offset": 569, "start": 45.36, "end": 45.52}, {"word": "There", "start_offset": 649, "end_offset": 655, "start": 51.92, "end": 52.4}, {"word": "she", "start_offset": 655, "end_offset": 659, "start": 52.4, "end": 52.72}, {"word": "is.", "start_offset": 659, "end_offset": 663, "start": 52.72, "end": 53.04}, {"word": "Now", "start_offset": 671, "end_offset": 679, "start": 53.68, "end": 54.32}, {"word": "you", "start_offset": 692, "end_offset": 696, "start": 55.36, "end": 55.68}, {"word": "love", "start_offset": 696, "end_offset": 700, "start": 55.68, "end": 56.0}, {"word": "her.", "start_offset": 704, "end_offset": 708, "start": 56.32, "end": 56.64}, {"word": "She's", "start_offset": 716, "end_offset": 723, "start": 57.28, "end": 57.84}, {"word": "your", "start_offset": 723, "end_offset": 726, "start": 57.84, "end": 58.08}, {"word": "passion.", "start_offset": 726, "end_offset": 732, "start": 58.08, "end": 58.56}, {"word": "Be", "start_offset": 739, "end_offset": 743, "start": 59.120000000000005, "end": 59.44}, {"word": "tender", "start_offset": 748, "end_offset": 753, "start": 59.84, "end": 60.24}, {"word": "to", "start_offset": 755, "end_offset": 759, "start": 60.4, "end": 60.72}, {"word": "her.", "start_offset": 759, "end_offset": 763, "start": 60.72, "end": 61.04}, {"word": "Be", "start_offset": 767, "end_offset": 771, "start": 61.36, "end": 61.68}, {"word": "honest.", "start_offset": 771, "end_offset": 777, "start": 61.68, "end": 62.160000000000004}, {"word": "Be", "start_offset": 794, "end_offset": 797, "start": 63.52, "end": 63.76}, {"word": "tender.", "start_offset": 800, "end_offset": 806, "start": 64.0, "end": 64.48}, {"word": "Remind", "start_offset": 819, "end_offset": 828, "start": 65.52, "end": 66.24}, {"word": "her", "start_offset": 828, "end_offset": 832, "start": 66.24, "end": 66.56}, {"word": "what", "start_offset": 836, "end_offset": 839, "start": 66.88, "end": 67.12}, {"word": "love", "start_offset": 843, "end_offset": 847, "start": 67.44, "end": 67.76}, {"word": "is.", "start_offset": 847, "end_offset": 850, "start": 67.76, "end": 68.0}], "segment": [{"segment": "Are you ready?", "start_offset": 140, "end_offset": 153, "start": 11.200000000000001, "end": 12.24}, {"segment": "Of course you're ready.", "start_offset": 156, "end_offset": 169, "start": 12.48, "end": 13.52}, {"segment": "You're a rock star.", "start_offset": 170, "end_offset": 184, "start": 13.6, "end": 14.72}, {"segment": "How's it looking, Barney?", "start_offset": 211, "end_offset": 229, "start": 16.88, "end": 18.32}, {"segment": "We should have about ten minutes.", "start_offset": 235, "end_offset": 262, "start": 18.8, "end": 20.96}, {"segment": "Well, that's perfect.", "start_offset": 269, "end_offset": 290, "start": 21.52, "end": 23.2}, {"segment": "We're only one.", "start_offset": 294, "end_offset": 309, "start": 23.52, "end": 24.72}, {"segment": "All systems go.", "start_offset": 314, "end_offset": 330, "start": 25.12, "end": 26.400000000000002}, {"segment": "Yeah, you go.", "start_offset": 331, "end_offset": 346, "start": 26.48, "end": 27.68}, {"segment": "Go.", "start_offset": 351, "end_offset": 355, "start": 28.080000000000002, "end": 28.400000000000002}, {"segment": "That's nice.", "start_offset": 535, "end_offset": 551, "start": 42.800000000000004, "end": 44.08}, {"segment": "Nothing to worry about.", "start_offset": 556, "end_offset": 569, "start": 44.480000000000004, "end": 45.52}, {"segment": "There she is.", "start_offset": 649, "end_offset": 663, "start": 51.92, "end": 53.04}, {"segment": "Now you love her.", "start_offset": 671, "end_offset": 708, "start": 53.68, "end": 56.64}, {"segment": "She's your passion.", "start_offset": 716, "end_offset": 732, "start": 57.28, "end": 58.56}, {"segment": "Be tender to her.", "start_offset": 739, "end_offset": 763, "start": 59.120000000000005, "end": 61.04}, {"segment": "Be honest.", "start_offset": 767, "end_offset": 777, "start": 61.36, "end": 62.160000000000004}, {"segment": "Be tender.", "start_offset": 794, "end_offset": 806, "start": 63.52, "end": 64.48}, {"segment": "Remind her what love is.", "start_offset": 819, "end_offset": 850, "start": 65.52, "end": 68.0}]}}

Performance Metrics

24.22s Prediction Time
101.54s Total Time
All Input Parameters
{
  "end_time": 300,
  "m3u8_url": "https://demo.unified-streaming.com/k8s/features/stable/video/tears-of-steel/tears-of-steel.ism/.m3u8",
  "start_time": 180,
  "timestamps": true
}
Input Parameters
end_time Type: number
End time in seconds for the time window
m3u8_url Type: string
URL to the m3u8 playlist file (supports .m4s and .ts segments)
audio_file Type: string
Audio file (wav, flac, mp3)
start_time Type: number
Start time in seconds for the time window
timestamps Type: booleanDefault: false
Whether to include timestamps in the transcription
Output Schema

Output

Type: string

Example Execution Logs
here
Extracting audio from m3u8 playlist: https://demo.unified-streaming.com/k8s/features/stable/video/tears-of-steel/tears-of-steel.ism/.m3u8
Running FFmpeg command: ffmpeg -y -protocol_whitelist file,http,https,tcp,tls -i https://demo.unified-streaming.com/k8s/features/stable/video/tears-of-steel/tears-of-steel.ism/.m3u8 -ss 180.0 -to 300.0 -acodec pcm_s16le -ar 16000 -ac 1 /tmp/m3u8_extracted_audio_6b8def2a1943c82970cc04e8b02a14d0.wav
Successfully extracted audio to: /tmp/m3u8_extracted_audio_6b8def2a1943c82970cc04e8b02a14d0.wav
    Loss tdt_kwargs: {'fastemit_lambda': 0.0, 'clamp': -1.0, 'durations': [0, 1, 2, 3, 4], 'sigma': 0.02, 'omega': 0.1}
    Cuda graphs with while loops are disabled, decoding speed will be slower
    Reason: No `cuda-python` module. Please do `pip install cuda-python>=12.3`

Transcribing:   0%|          | 0/1 [00:00<?, ?it/s]
Transcribing: 100%|██████████| 1/1 [00:01<00:00,  1.80s/it]
Transcribing: 100%|██████████| 1/1 [00:01<00:00,  1.80s/it]
Version Details
Version ID
74e605e7e05d1a7f52a5a7bb5d741a8b5a087309bee88ebdd249f63835f8a90d
Version Created
August 25, 2025
Run on Replicate →