Transcribe audio

POST

https://api.assemblyai.com/v2/transcript

POST

/v2/transcript

1 import requests
2 
3 url = "https://api.assemblyai.com/v2/transcript"
4 
5 payload = {
6     "audio_url": "https://assembly.ai/wildfires.mp3",
7     "audio_end_at": 280,
8     "audio_start_from": 10,
9     "auto_chapters": True,
10     "auto_highlights": True,
11     "boost_param": "high",
12     "content_safety": True,
13     "custom_spelling": [],
14     "disfluencies": False,
15     "entity_detection": True,
16     "filter_profanity": True,
17     "format_text": True,
18     "iab_categories": True,
19     "language_code": "en_us",
20     "language_confidence_threshold": 0.7,
21     "language_detection": True,
22     "multichannel": True,
23     "punctuate": True,
24     "redact_pii": True,
25     "redact_pii_audio": True,
26     "redact_pii_audio_quality": "mp3",
27     "redact_pii_policies": ["us_social_security_number", "credit_card_number"],
28     "redact_pii_sub": "hash",
29     "sentiment_analysis": True,
30     "speaker_labels": True,
31     "speakers_expected": 2,
32     "speech_threshold": 0.5,
33     "summarization": True,
34     "summary_model": "informative",
35     "summary_type": "bullets",
36     "topics": [],
37     "webhook_auth_header_name": "webhook-secret",
38     "webhook_auth_header_value": "webhook-secret-value",
39     "webhook_url": "https://your-webhook-url/path",
40     "custom_topics": True,
41     "dual_channel": False,
42     "word_boost": ["aws", "azure", "google cloud"]
43 }
44 headers = {
45     "Authorization": "<apiKey>",
46     "Content-Type": "application/json"
47 }
48 
49 response = requests.post(url, json=payload, headers=headers)
50 
51 print(response.json())

Try it

200Successful

1 {
2   "id": "9ea68fd3-f953-42c1-9742-976c447fb463",
3   "audio_url": "https://assembly.ai/wildfires.mp3",
4   "status": "completed",
5   "language_confidence_threshold": 0.7,
6   "language_confidence": 0.9959,
7   "speech_model": null,
8   "webhook_auth": true,
9   "auto_highlights": true,
10   "redact_pii": true,
11   "summarization": true,
12   "language_model": "assemblyai_default",
13   "acoustic_model": "assemblyai_default",
14   "language_code": "en_us",
15   "language_detection": true,
16   "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning. What is it about the conditions right now that have caused this round of wildfires to affect so many people so far away? Well, there's a couple of things. The season has been pretty dry already. And then the fact that we're getting hit in the US. Is because there's a couple of weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the Mid Atlantic and the Northeast and kind of just dropping the smoke there. So what is it in this haze that makes it harmful? And I'm assuming it is harmful. It is. The levels outside right now in Baltimore are considered unhealthy. And most of that is due to what's called particulate matter, which are tiny particles, microscopic smaller than the width of your hair that can get into your lungs and impact your respiratory system, your cardiovascular system, and even your neurological your brain. What makes this particularly harmful? Is it the volume of particulant? Is it something in particular? What is it exactly? Can you just drill down on that a little bit more? Yeah. So the concentration of particulate matter I was looking at some of the monitors that we have was reaching levels of what are, in science, big 150 micrograms per meter cubed, which is more than ten times what the annual average should be and about four times higher than what you're supposed to have on a 24 hours average. And so the concentrations of these particles in the air are just much, much higher than we typically see. And exposure to those high levels can lead to a host of health problems. And who is most vulnerable? I noticed that in New York City, for example, they're canceling outdoor activities. And so here it is in the early days of summer, and they have to keep all the kids inside. So who tends to be vulnerable in a situation like this? It's the youngest. So children, obviously, whose bodies are still developing. The elderly, who are their bodies are more in decline and they're more susceptible to the health impacts of breathing, the poor air quality. And then people who have preexisting health conditions, people with respiratory conditions or heart conditions can be triggered by high levels of air pollution. Could this get worse? That's a good question. In some areas, it's much worse than others. And it just depends on kind of where the smoke is concentrated. I think New York has some of the higher concentrations right now, but that's going to change as that air moves away from the New York area. But over the course of the next few days, we will see different areas being hit at different times with the highest concentrations. I was going to ask you about more fires start burning. I don't expect the concentrations to go up too much higher. I was going to ask you how and you started to answer this, but how much longer could this last? Or forgive me if I'm asking you to speculate, but what do you think? Well, I think the fires are going to burn for a little bit longer, but the key for us in the US. Is the weather system changing. And so right now, it's kind of the weather systems that are pulling that air into our mid Atlantic and Northeast region. As those weather systems change and shift, we'll see that smoke going elsewhere and not impact us in this region as much. And so I think that's going to be the defining factor. And I think the next couple of days we're going to see a shift in that weather pattern and start to push the smoke away from where we are. And finally, with the impacts of climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences or circumstances? I mean, that is one of the predictions for climate change. Looking into the future, the fire season is starting earlier and lasting longer, and we're seeing more frequent fires. So, yeah, this is probably something that we'll be seeing more frequently. This tends to be much more of an issue in the Western US. So the eastern US. Getting hit right now is a little bit new. But yeah, I think with climate change moving forward, this is something that is going to happen more frequently. That's Peter De Carlo, associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Sergeant Carlo, thanks so much for joining us and sharing this expertise with us. Thank you for having me.",
17   "words": [
18     {
19       "confidence": 0.97465,
20       "start": 250,
21       "end": 650,
22       "text": "Smoke",
23       "speaker": null
24     },
25     {
26       "confidence": 0.99999,
27       "start": 730,
28       "end": 1022,
29       "text": "from",
30       "speaker": null
31     },
32     {
33       "confidence": 0.99844,
34       "start": 1076,
35       "end": 1418,
36       "text": "hundreds",
37       "speaker": null
38     },
39     {
40       "confidence": 0.84,
41       "start": 1434,
42       "end": 1614,
43       "text": "of",
44       "speaker": null
45     },
46     {
47       "confidence": 0.89572,
48       "start": 1652,
49       "end": 2346,
50       "text": "wildfires",
51       "speaker": null
52     },
53     {
54       "confidence": 0.99994,
55       "start": 2378,
56       "end": 2526,
57       "text": "in",
58       "speaker": null
59     },
60     {
61       "confidence": 0.93953,
62       "start": 2548,
63       "end": 3130,
64       "text": "Canada",
65       "speaker": null
66     },
67     {
68       "confidence": 0.999,
69       "start": 3210,
70       "end": 3454,
71       "text": "is",
72       "speaker": null
73     },
74     {
75       "confidence": 0.74794,
76       "start": 3492,
77       "end": 3946,
78       "text": "triggering",
79       "speaker": null
80     },
81     {
82       "confidence": 1,
83       "start": 3978,
84       "end": 4174,
85       "text": "air",
86       "speaker": null
87     },
88     {
89       "confidence": 0.88077,
90       "start": 4212,
91       "end": 4558,
92       "text": "quality",
93       "speaker": null
94     },
95     {
96       "confidence": 0.94814,
97       "start": 4644,
98       "end": 5114,
99       "text": "alerts",
100       "speaker": null
101     },
102     {
103       "confidence": 0.99726,
104       "start": 5162,
105       "end": 5466,
106       "text": "throughout",
107       "speaker": null
108     },
109     {
110       "confidence": 0.79,
111       "start": 5498,
112       "end": 5694,
113       "text": "the",
114       "speaker": null
115     },
116     {
117       "confidence": 0.89,
118       "start": 5732,
119       "end": 6382,
120       "text": "US.",
121       "speaker": null
122     }
123   ],
124   "utterances": [
125     {
126       "confidence": 0.9359033333333334,
127       "start": 250,
128       "end": 26950,
129       "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor.",
130       "words": [
131         {
132           "confidence": 0.97503,
133           "start": 250,
134           "end": 650,
135           "text": "Smoke",
136           "speaker": "A"
137         },
138         {
139           "confidence": 0.99999,
140           "start": 730,
141           "end": 1022,
142           "text": "from",
143           "speaker": "A"
144         },
145         {
146           "confidence": 0.99843,
147           "start": 1076,
148           "end": 1418,
149           "text": "hundreds",
150           "speaker": "A"
151         },
152         {
153           "confidence": 0.85,
154           "start": 1434,
155           "end": 1614,
156           "text": "of",
157           "speaker": "A"
158         },
159         {
160           "confidence": 0.89657,
161           "start": 1652,
162           "end": 2346,
163           "text": "wildfires",
164           "speaker": "A"
165         },
166         {
167           "confidence": 0.99994,
168           "start": 2378,
169           "end": 2526,
170           "text": "in",
171           "speaker": "A"
172         },
173         {
174           "confidence": 0.93864,
175           "start": 2548,
176           "end": 3130,
177           "text": "Canada",
178           "speaker": "A"
179         },
180         {
181           "confidence": 0.999,
182           "start": 3210,
183           "end": 3454,
184           "text": "is",
185           "speaker": "A"
186         },
187         {
188           "confidence": 0.75366,
189           "start": 3492,
190           "end": 3946,
191           "text": "triggering",
192           "speaker": "A"
193         },
194         {
195           "confidence": 1,
196           "start": 3978,
197           "end": 4174,
198           "text": "air",
199           "speaker": "A"
200         },
201         {
202           "confidence": 0.87745,
203           "start": 4212,
204           "end": 4558,
205           "text": "quality",
206           "speaker": "A"
207         },
208         {
209           "confidence": 0.94739,
210           "start": 4644,
211           "end": 5114,
212           "text": "alerts",
213           "speaker": "A"
214         },
215         {
216           "confidence": 0.99726,
217           "start": 5162,
218           "end": 5466,
219           "text": "throughout",
220           "speaker": "A"
221         },
222         {
223           "confidence": 0.79,
224           "start": 5498,
225           "end": 5694,
226           "text": "the",
227           "speaker": "A"
228         },
229         {
230           "confidence": 0.88,
231           "start": 5732,
232           "end": 6382,
233           "text": "US.",
234           "speaker": "A"
235         }
236       ],
237       "speaker": "A"
238     }
239   ],
240   "confidence": 0.9404651451800253,
241   "audio_duration": 281,
242   "punctuate": true,
243   "format_text": true,
244   "disfluencies": false,
245   "multichannel": false,
246   "webhook_url": "https://your-webhook-url.tld/path",
247   "webhook_status_code": 200,
248   "webhook_auth_header_name": "webhook-secret",
249   "auto_highlights_result": {
250     "status": "success",
251     "results": [
252       {
253         "count": 1,
254         "rank": 0.08,
255         "text": "air quality alerts",
256         "timestamps": [
257           {
258             "start": 3978,
259             "end": 5114
260           }
261         ]
262       },
263       {
264         "count": 1,
265         "rank": 0.08,
266         "text": "wide ranging air quality consequences",
267         "timestamps": [
268           {
269             "start": 235388,
270             "end": 238694
271           }
272         ]
273       },
274       {
275         "count": 1,
276         "rank": 0.07,
277         "text": "more wildfires",
278         "timestamps": [
279           {
280             "start": 230972,
281             "end": 232354
282           }
283         ]
284       },
285       {
286         "count": 1,
287         "rank": 0.07,
288         "text": "air pollution",
289         "timestamps": [
290           {
291             "start": 156004,
292             "end": 156910
293           }
294         ]
295       },
296       {
297         "count": 3,
298         "rank": 0.07,
299         "text": "weather systems",
300         "timestamps": [
301           {
302             "start": 47344,
303             "end": 47958
304           },
305           {
306             "start": 205268,
307             "end": 205818
308           },
309           {
310             "start": 211588,
311             "end": 213434
312           }
313         ]
314       },
315       {
316         "count": 2,
317         "rank": 0.06,
318         "text": "high levels",
319         "timestamps": [
320           {
321             "start": 121128,
322             "end": 121646
323           },
324           {
325             "start": 155412,
326             "end": 155866
327           }
328         ]
329       },
330       {
331         "count": 1,
332         "rank": 0.06,
333         "text": "health conditions",
334         "timestamps": [
335           {
336             "start": 152138,
337             "end": 152666
338           }
339         ]
340       },
341       {
342         "count": 2,
343         "rank": 0.06,
344         "text": "Peter de Carlo",
345         "timestamps": [
346           {
347             "start": 18948,
348             "end": 19930
349           },
350           {
351             "start": 268298,
352             "end": 269194
353           }
354         ]
355       },
356       {
357         "count": 1,
358         "rank": 0.06,
359         "text": "New York City",
360         "timestamps": [
361           {
362             "start": 125768,
363             "end": 126274
364           }
365         ]
366       },
367       {
368         "count": 1,
369         "rank": 0.05,
370         "text": "respiratory conditions",
371         "timestamps": [
372           {
373             "start": 152964,
374             "end": 153786
375           }
376         ]
377       },
378       {
379         "count": 3,
380         "rank": 0.05,
381         "text": "New York",
382         "timestamps": [
383           {
384             "start": 125768,
385             "end": 126034
386           },
387           {
388             "start": 171448,
389             "end": 171938
390           },
391           {
392             "start": 176008,
393             "end": 176322
394           }
395         ]
396       },
397       {
398         "count": 3,
399         "rank": 0.05,
400         "text": "climate change",
401         "timestamps": [
402           {
403             "start": 229548,
404             "end": 230230
405           },
406           {
407             "start": 244576,
408             "end": 245162
409           },
410           {
411             "start": 263348,
412             "end": 263950
413           }
414         ]
415       },
416       {
417         "count": 1,
418         "rank": 0.05,
419         "text": "Johns Hopkins University Varsity",
420         "timestamps": [
421           {
422             "start": 23972,
423             "end": 25490
424           }
425         ]
426       },
427       {
428         "count": 1,
429         "rank": 0.05,
430         "text": "heart conditions",
431         "timestamps": [
432           {
433             "start": 153988,
434             "end": 154506
435           }
436         ]
437       },
438       {
439         "count": 1,
440         "rank": 0.05,
441         "text": "air quality warnings",
442         "timestamps": [
443           {
444             "start": 12308,
445             "end": 13434
446           }
447         ]
448       }
449     ]
450   },
451   "audio_start_from": 10,
452   "audio_end_at": 280,
453   "boost_param": "high",
454   "filter_profanity": true,
455   "redact_pii_audio": true,
456   "redact_pii_audio_quality": "mp3",
457   "redact_pii_policies": [
458     "us_social_security_number",
459     "credit_card_number"
460   ],
461   "redact_pii_sub": "hash",
462   "speaker_labels": true,
463   "speakers_expected": 2,
464   "content_safety": true,
465   "content_safety_labels": {
466     "status": "success",
467     "results": [
468       {
469         "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
470         "labels": [
471           {
472             "label": "disasters",
473             "confidence": 0.8142836093902588,
474             "severity": 0.4093044400215149
475           }
476         ],
477         "sentences_idx_start": 0,
478         "sentences_idx_end": 5,
479         "timestamp": {
480           "start": 250,
481           "end": 28840
482         }
483       }
484     ],
485     "summary": {
486       "disasters": 0.9940800441842205,
487       "health_issues": 0.9216489289040967
488     },
489     "severity_score_summary": {
490       "disasters": {
491         "low": 0.5733263024656846,
492         "medium": 0.42667369753431533,
493         "high": 0
494       },
495       "health_issues": {
496         "low": 0.22863814977924785,
497         "medium": 0.45014154926938227,
498         "high": 0.32122030095136983
499       }
500     }
501   },
502   "iab_categories": true,
503   "iab_categories_result": {
504     "status": "success",
505     "results": [
506       {
507         "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning.",
508         "labels": [
509           {
510             "relevance": 0.988274097442627,
511             "label": "Home&Garden>IndoorEnvironmentalQuality"
512           },
513           {
514             "relevance": 0.5821335911750793,
515             "label": "NewsAndPolitics>Weather"
516           },
517           {
518             "relevance": 0.0042327106930315495,
519             "label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth"
520           },
521           {
522             "relevance": 0.0033971222583204508,
523             "label": "NewsAndPolitics>Disasters"
524           },
525           {
526             "relevance": 0.002469958271831274,
527             "label": "BusinessAndFinance>Business>GreenSolutions"
528           },
529           {
530             "relevance": 0.0014376690378412604,
531             "label": "MedicalHealth>DiseasesAndConditions>Cancer"
532           },
533           {
534             "relevance": 0.0014294233405962586,
535             "label": "Science>Environment"
536           },
537           {
538             "relevance": 0.001234519761055708,
539             "label": "Travel>TravelLocations>PolarTravel"
540           },
541           {
542             "relevance": 0.0010231725173071027,
543             "label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu"
544           },
545           {
546             "relevance": 0.0007445293595083058,
547             "label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry"
548           }
549         ],
550         "timestamp": {
551           "start": 250,
552           "end": 28840
553         }
554       }
555     ],
556     "summary": {
557       "NewsAndPolitics>Weather": 1,
558       "Home&Garden>IndoorEnvironmentalQuality": 0.9043831825256348,
559       "Science>Environment": 0.16117265820503235,
560       "BusinessAndFinance>Industries>EnvironmentalServicesIndustry": 0.14393523335456848,
561       "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth": 0.11401086300611496,
562       "BusinessAndFinance>Business>GreenSolutions": 0.06348437070846558,
563       "NewsAndPolitics>Disasters": 0.05041387677192688,
564       "Travel>TravelLocations>PolarTravel": 0.01308488193899393,
565       "HealthyLiving": 0.008222488686442375,
566       "MedicalHealth>DiseasesAndConditions>ColdAndFlu": 0.0022315620444715023,
567       "MedicalHealth>DiseasesAndConditions>HeartAndCardiovascularDiseases": 0.00213034451007843,
568       "HealthyLiving>Wellness>SmokingCessation": 0.001540527562610805,
569       "MedicalHealth>DiseasesAndConditions>Injuries": 0.0013950627762824297,
570       "BusinessAndFinance>Industries>PowerAndEnergyIndustry": 0.0012570273829624057,
571       "MedicalHealth>DiseasesAndConditions>Cancer": 0.001097781932912767,
572       "MedicalHealth>DiseasesAndConditions>Allergies": 0.0010148967849090695,
573       "MedicalHealth>DiseasesAndConditions>MentalHealth": 0.000717321818228811,
574       "Style&Fashion>PersonalCare>DeodorantAndAntiperspirant": 0.0006022014422342181,
575       "Technology&Computing>Computing>ComputerNetworking": 0.0005461975233629346,
576       "MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877
577     }
578   },
579   "auto_chapters": true,
580   "chapters": [
581     {
582       "gist": "Smoggy air quality alerts across US",
583       "headline": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts across US",
584       "summary": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. In some places, the air quality warnings include the warning to stay inside.",
585       "start": 250,
586       "end": 28840
587     },
588     {
589       "gist": "What is it about the conditions right now that have caused this round",
590       "headline": "High particulate matter in wildfire smoke can lead to serious health problems",
591       "summary": "Air pollution levels in Baltimore are considered unhealthy. Exposure to high levels can lead to a host of health problems. With climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences?",
592       "start": 29610,
593       "end": 280340
594     }
595   ],
596   "summary_type": "bullets",
597   "summary_model": "informative",
598   "summary": "- Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. In some places, the air quality warnings include the warning to stay inside.\\n- Air pollution levels in Baltimore are considered unhealthy. Exposure to high levels can lead to a host of health problems. With climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences?",
599   "topics": [],
600   "sentiment_analysis": true,
601   "entity_detection": true,
602   "entities": [
603     {
604       "entity_type": "location",
605       "text": "Canada",
606       "start": 2548,
607       "end": 3130
608     },
609     {
610       "entity_type": "location",
611       "text": "the US",
612       "start": 5498,
613       "end": 6382
614     },
615     {
616       "entity_type": "location",
617       "text": "Maine",
618       "start": 7492,
619       "end": 7914
620     },
621     {
622       "entity_type": "location",
623       "text": "Maryland",
624       "start": 8212,
625       "end": 8634
626     },
627     {
628       "entity_type": "location",
629       "text": "Minnesota",
630       "start": 8932,
631       "end": 9578
632     },
633     {
634       "entity_type": "person_name",
635       "text": "Peter de Carlo",
636       "start": 18948,
637       "end": 19930
638     },
639     {
640       "entity_type": "occupation",
641       "text": "associate professor",
642       "start": 20292,
643       "end": 21194
644     },
645     {
646       "entity_type": "organization",
647       "text": "Department of Environmental Health and Engineering",
648       "start": 21508,
649       "end": 23706
650     },
651     {
652       "entity_type": "organization",
653       "text": "Johns Hopkins University Varsity",
654       "start": 23972,
655       "end": 25490
656     },
657     {
658       "entity_type": "occupation",
659       "text": "professor",
660       "start": 26076,
661       "end": 26950
662     },
663     {
664       "entity_type": "location",
665       "text": "the US",
666       "start": 45184,
667       "end": 45898
668     },
669     {
670       "entity_type": "nationality",
671       "text": "Canadian",
672       "start": 49728,
673       "end": 50086
674     }
675   ],
676   "speech_threshold": 0.5,
677   "dual_channel": false,
678   "word_boost": [
679     "aws",
680     "azure",
681     "google cloud"
682   ],
683   "custom_topics": true
684 }

To use our EU server for transcription, replace api.assemblyai.com with api.eu.assemblyai.com.

Create a transcript from a media file that is accessible via a URL.

<Note>To use our EU server for transcription, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.</Note> Create a transcript from a media file that is accessible via a URL.

Authentication

Authorizationstring

API Key authentication via header

Request

Params to create a transcript

audio_urlstringRequiredformat: "url"

The URL of the audio or video file to transcribe.

audio_end_atintegerOptional

The point in time, in milliseconds, to stop transcribing in your media file

audio_start_fromintegerOptional

The point in time, in milliseconds, to begin transcribing in your media file

auto_chaptersbooleanOptionalDefaults to false

Enable Auto Chapters, can be true or false

Enable [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters), can be true or false

auto_highlightsbooleanOptionalDefaults to false

Enable Key Phrases, either true or false

boost_paramenumOptional

How much to boost specified words

Allowed values:

content_safetybooleanOptionalDefaults to false

Enable Content Moderation, can be true or false

Enable [Content Moderation](https://www.assemblyai.com/docs/models/content-moderation), can be true or false

content_safety_confidenceintegerOptional25-100Defaults to 50

The confidence threshold for the Content Moderation model. Values must be between 25 and 100.

custom_spellinglist of objectsOptional

Customize how words are spelled and formatted using to and from values

disfluenciesbooleanOptionalDefaults to false

Transcribe Filler Words, like “umm”, in your media file; can be true or false

entity_detectionbooleanOptionalDefaults to false

Enable Entity Detection, can be true or false

Enable [Entity Detection](https://www.assemblyai.com/docs/models/entity-detection), can be true or false

filter_profanitybooleanOptionalDefaults to false

Filter profanity from the transcribed text, can be true or false

format_textbooleanOptionalDefaults to true

Enable Text Formatting, can be true or false

iab_categoriesbooleanOptionalDefaults to false

Enable Topic Detection, can be true or false

Enable [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection), can be true or false

keyterms_promptlist of stringsOptional

keyterms_prompt is only supported when the speech_model is specified as slam-1

Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).

<Warning>`keyterms_prompt` is only supported when the `speech_model` is specified as `slam-1`</Warning> Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).

language_codeenum or nullOptional

The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.

The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages). The default value is 'en_us'.

language_confidence_thresholddoubleOptional

The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0.

language_detectionbooleanOptionalDefaults to false

Enable Automatic language detection, either true or false.

Enable [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection), either true or false.

multichannelbooleanOptionalDefaults to false

Enable Multichannel transcription, can be true or false.

Enable [Multichannel](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) transcription, can be true or false.

punctuatebooleanOptionalDefaults to true

Enable Automatic Punctuation, can be true or false

redact_piibooleanOptionalDefaults to false

Redact PII from the transcribed text using the Redact PII model, can be true or false

redact_pii_audiobooleanOptionalDefaults to false

Generate a copy of the original media file with spoken PII “beeped” out, can be true or false. See PII redaction for more details.

Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

redact_pii_audio_optionsobjectOptional

Specify options for PII redacted audio files.

redact_pii_audio_qualityenumOptional

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See PII redaction for more details.

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

Allowed values:

redact_pii_policieslist of enumsOptional

The list of PII Redaction policies to enable. See PII redaction for more details.

The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

redact_pii_subenum or nullOptional

The replacement logic for detected PII, can be entity_type or hash. See PII redaction for more details.

The replacement logic for detected PII, can be `entity_type` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

Allowed values:

sentiment_analysisbooleanOptionalDefaults to false

Enable Sentiment Analysis, can be true or false

Enable [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis), can be true or false

speaker_labelsbooleanOptionalDefaults to false

Enable Speaker diarization, can be true or false

Enable [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization), can be true or false

speaker_optionsobjectOptional

Specify options for speaker diarization.

speakers_expectedinteger or nullOptional

Tells the speaker label model how many speakers it should attempt to identify. See Speaker diarization for more details.

Tells the speaker label model how many speakers it should attempt to identify. See [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for more details.

speech_modelenum or nullOptional

The speech model to use for the transcription. When null, the universal model is used.

Allowed values:

speech_thresholddouble or nullOptional

Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.

summarizationbooleanOptionalDefaults to false

Enable Summarization, can be true or false

Enable [Summarization](https://www.assemblyai.com/docs/models/summarization), can be true or false

summary_modelenumOptional

The model to summarize the transcript

Allowed values:

summary_typeenumOptional

The type of summary

Allowed values:

topicslist of stringsOptional

The list of custom topics

webhook_auth_header_namestring or nullOptional

The header name to be sent with the transcript completed or failed webhook requests

webhook_auth_header_valuestring or nullOptional

The header value to send back with the transcript completed or failed webhook requests for added security

webhook_urlstringOptionalformat: "url"

The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.

custom_topicsbooleanOptionalDefaults to falseDeprecated

Enable custom topics, either true or false

dual_channelbooleanOptionalDefaults to falseDeprecated

Enable Dual Channel transcription, can be true or false.

Enable [Dual Channel](https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) transcription, can be true or false.

promptstringOptionalDeprecated

This parameter does not currently have any functionality attached to it.

word_boostlist of stringsOptionalDeprecated

The list of custom vocabulary to boost transcription probability for

Response

Transcript created and queued for processing

idstringformat: "uuid"

The unique identifier of your transcript

audio_urlstringformat: "url"

The URL of the media that was transcribed

statusenum

The status of your transcript. Possible values are queued, processing, completed, or error.

Allowed values:

language_confidence_thresholddouble or null

The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold.

language_confidencedouble or null0-1

The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence)

speech_modelenum or null

The speech model used for the transcription. When null, the universal model is used.

Allowed values:

webhook_authboolean

Whether webhook authentication details were provided

auto_highlightsboolean

Whether Key Phrases is enabled, either true or false

redact_piiboolean

Whether PII Redaction is enabled, either true or false

Whether [PII Redaction](https://www.assemblyai.com/docs/models/pii-redaction) is enabled, either true or false

summarizationboolean

Whether Summarization is enabled, either true or false

Whether [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled, either true or false

language_modelstringDeprecated

The language model that was used for the transcript

acoustic_modelstringDeprecated

The acoustic model that was used for the transcript

language_codeenum or null

The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.

The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/concepts/supported-languages). The default value is 'en_us'.

language_detectionboolean or null

Whether Automatic language detection is enabled, either true or false

Whether [Automatic language detection](https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) is enabled, either true or false

textstring or null

The textual transcript of your media file

wordslist of objects or null

An array of temporally-sequential word objects, one for each word in the transcript. See Speech recognition for more information.

An array of temporally-sequential word objects, one for each word in the transcript. See [Speech recognition](https://www.assemblyai.com/docs/models/speech-recognition) for more information.

utteranceslist of objects or null

When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects. See Speaker diarization and Multichannel transcription for more information.

When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects. See [Speaker diarization](https://www.assemblyai.com/docs/speech-to-text/speaker-diarization) and [Multichannel transcription](https://www.assemblyai.com/docs/speech-to-text/speech-recognition#multichannel-transcription) for more information.

confidencedouble or null0-1

The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)

audio_durationinteger or null

The duration of this transcript object's media file, in seconds

punctuateboolean or null

Whether Automatic Punctuation is enabled, either true or false

format_textboolean or null

Whether Text Formatting is enabled, either true or false

disfluenciesboolean or null

Transcribe Filler Words, like “umm”, in your media file; can be true or false

multichannelboolean or null

Whether Multichannel transcription was enabled in the transcription request, either true or false

Whether [Multichannel transcription](https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription) was enabled in the transcription request, either true or false

audio_channelsinteger or null

The number of audio channels in the audio file. This is only present when multichannel is enabled.

webhook_urlstring or nullformat: "url"

webhook_status_codeinteger or null

The status code we received from your server when delivering the transcript completed or failed webhook request, if a webhook URL was provided

webhook_auth_header_namestring or null

The header name to be sent with the transcript completed or failed webhook requests

auto_highlights_resultobject or null

An array of results for the Key Phrases model, if it is enabled. See Key Phrases for more information.

An array of results for the Key Phrases model, if it is enabled. See [Key Phrases](https://www.assemblyai.com/docs/models/key-phrases) for more information.

audio_start_frominteger or null

The point in time, in milliseconds, in the file at which the transcription was started

audio_end_atinteger or null

The point in time, in milliseconds, in the file at which the transcription was terminated

boost_paramstring or null

The word boost parameter value

filter_profanityboolean or null

Whether Profanity Filtering is enabled, either true or false

Whether [Profanity Filtering](https://www.assemblyai.com/docs/models/speech-recognition#profanity-filtering) is enabled, either true or false

redact_pii_audioboolean or null

Whether a redacted version of the audio file was generated, either true or false. See PII redaction for more information.

Whether a redacted version of the audio file was generated, either true or false. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more information.

redact_pii_audio_qualityenum or null

The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled. See PII redaction for more information.

The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more information.

Allowed values:

redact_pii_policieslist of enums or null

The list of PII Redaction policies that were enabled, if PII Redaction is enabled. See PII redaction for more information.

The list of PII Redaction policies that were enabled, if PII Redaction is enabled. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more information.

redact_pii_subenum or null

The replacement logic for detected PII, can be entity_type or hash. See PII redaction for more details.

The replacement logic for detected PII, can be `entity_type` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/models/pii-redaction) for more details.

Allowed values:

speaker_labelsboolean or null

Whether Speaker diarization is enabled, can be true or false

Whether [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization) is enabled, can be true or false

speakers_expectedinteger or null

Tell the speaker label model how many speakers it should attempt to identify. See Speaker diarization for more details.

Tell the speaker label model how many speakers it should attempt to identify. See [Speaker diarization](https://www.assemblyai.com/docs/models/speaker-diarization) for more details.

content_safetyboolean or null

Whether Content Moderation is enabled, can be true or false

Whether [Content Moderation](https://www.assemblyai.com/docs/models/content-moderation) is enabled, can be true or false

content_safety_labelsobject or null

An array of results for the Content Moderation model, if it is enabled. See Content moderation for more information.

An array of results for the Content Moderation model, if it is enabled. See [Content moderation](https://www.assemblyai.com/docs/models/content-moderation) for more information.

iab_categoriesboolean or null

Whether Topic Detection is enabled, can be true or false

Whether [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) is enabled, can be true or false

iab_categories_resultobject or null

The result of the Topic Detection model, if it is enabled. See Topic Detection for more information.

The result of the Topic Detection model, if it is enabled. See [Topic Detection](https://www.assemblyai.com/docs/models/topic-detection) for more information.

custom_spellinglist of objects or null

Customize how words are spelled and formatted using to and from values

keyterms_promptlist of strings or null

Improve accuracy with up to 1000 domain-specific words or phrases (maximum 6 words per phrase).

auto_chaptersboolean or null

Whether Auto Chapters is enabled, can be true or false

Whether [Auto Chapters](https://www.assemblyai.com/docs/models/auto-chapters) is enabled, can be true or false

chapterslist of objects or null

An array of temporally sequential chapters for the audio file

summary_typestring or null

The type of summary generated, if Summarization is enabled

The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled

summary_modelstring or null

The Summarization model used to generate the summary, if Summarization is enabled

The Summarization model used to generate the summary, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled

summarystring or null

The generated summary of the media file, if Summarization is enabled

The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/models/summarization) is enabled

topicslist of strings or null

The list of custom topics provided if custom topics is enabled

sentiment_analysisboolean or null

Whether Sentiment Analysis is enabled, can be true or false

Whether [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis) is enabled, can be true or false

sentiment_analysis_resultslist of objects or null

An array of results for the Sentiment Analysis model, if it is enabled. See Sentiment Analysis for more information.

An array of results for the Sentiment Analysis model, if it is enabled. See [Sentiment Analysis](https://www.assemblyai.com/docs/models/sentiment-analysis) for more information.

entity_detectionboolean or null

Whether Entity Detection is enabled, can be true or false

Whether [Entity Detection](https://www.assemblyai.com/docs/models/entity-detection) is enabled, can be true or false

entitieslist of objects or null

An array of results for the Entity Detection model, if it is enabled. See Entity detection for more information.

An array of results for the Entity Detection model, if it is enabled. See [Entity detection](https://www.assemblyai.com/docs/models/entity-detection) for more information.

speech_thresholddouble or null

Defaults to null. Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.

throttledboolean or null

True while a request is throttled and false when a request is no longer throttled

errorstring or null

Error message of why the transcript failed

dual_channelboolean or nullDeprecated

Whether Dual channel transcription was enabled in the transcription request, either true or false

Whether [Dual channel transcription](https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) was enabled in the transcription request, either true or false

speed_boostboolean or nullDeprecated

Whether speed boost is enabled

word_boostlist of strings or nullDeprecated

The list of custom vocabulary to boost transcription probability for

promptstring or nullDeprecated

This parameter does not currently have any functionality attached to it.

custom_topicsboolean or nullDeprecated

Whether custom topics is enabled, either true or false

Authentication

Request

Response

Errors