For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundChangelogSign In
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
  • API Reference
    • Overview
      • POSTTranscribe audio
      • GETGet transcript
      • GETGet sentences in transcript
      • GETGet paragraphs in transcript
      • GETGet subtitles for transcript
      • GETGet redacted audio
      • GETSearch words in transcript
      • GETList transcripts
      • DELDelete transcript
LogoLogo
PlaygroundChangelogSign In
API ReferenceTranscripts

Get transcript

GET
https://api.assemblyai.com/v2/transcript/:transcript_id
GET
/v2/transcript/:transcript_id
$curl https://api.assemblyai.com/v2/transcript/transcript_id \
>     -H "Authorization: <apiKey>"
1{
2  "audio_url": "https://assembly.ai/wildfires.mp3",
3  "auto_highlights": true,
4  "id": "9ea68fd3-f953-42c1-9742-976c447fb463",
5  "language_confidence": 0.9959,
6  "language_confidence_threshold": 0.7,
7  "redact_pii": true,
8  "status": "completed",
9  "webhook_auth": true,
10  "summarization": false,
11  "acoustic_model": "assemblyai_default",
12  "language_model": "assemblyai_default",
13  "speech_model": null,
14  "audio_duration": 281,
15  "audio_end_at": 280,
16  "audio_start_from": 10,
17  "auto_highlights_result": {
18    "status": "success",
19    "results": [
20      {
21        "count": 1,
22        "rank": 0.08,
23        "text": "air quality alerts",
24        "timestamps": [
25          {
26            "start": 3978,
27            "end": 5114
28          }
29        ]
30      },
31      {
32        "count": 1,
33        "rank": 0.08,
34        "text": "wide ranging air quality consequences",
35        "timestamps": [
36          {
37            "start": 235388,
38            "end": 238694
39          }
40        ]
41      },
42      {
43        "count": 1,
44        "rank": 0.07,
45        "text": "more wildfires",
46        "timestamps": [
47          {
48            "start": 230972,
49            "end": 232354
50          }
51        ]
52      },
53      {
54        "count": 1,
55        "rank": 0.07,
56        "text": "air pollution",
57        "timestamps": [
58          {
59            "start": 156004,
60            "end": 156910
61          }
62        ]
63      },
64      {
65        "count": 3,
66        "rank": 0.07,
67        "text": "weather systems",
68        "timestamps": [
69          {
70            "start": 47344,
71            "end": 47958
72          },
73          {
74            "start": 205268,
75            "end": 205818
76          },
77          {
78            "start": 211588,
79            "end": 213434
80          }
81        ]
82      },
83      {
84        "count": 2,
85        "rank": 0.06,
86        "text": "high levels",
87        "timestamps": [
88          {
89            "start": 121128,
90            "end": 121646
91          },
92          {
93            "start": 155412,
94            "end": 155866
95          }
96        ]
97      },
98      {
99        "count": 1,
100        "rank": 0.06,
101        "text": "health conditions",
102        "timestamps": [
103          {
104            "start": 152138,
105            "end": 152666
106          }
107        ]
108      },
109      {
110        "count": 2,
111        "rank": 0.06,
112        "text": "Peter de Carlo",
113        "timestamps": [
114          {
115            "start": 18948,
116            "end": 19930
117          },
118          {
119            "start": 268298,
120            "end": 269194
121          }
122        ]
123      },
124      {
125        "count": 1,
126        "rank": 0.06,
127        "text": "New York City",
128        "timestamps": [
129          {
130            "start": 125768,
131            "end": 126274
132          }
133        ]
134      },
135      {
136        "count": 1,
137        "rank": 0.05,
138        "text": "respiratory conditions",
139        "timestamps": [
140          {
141            "start": 152964,
142            "end": 153786
143          }
144        ]
145      },
146      {
147        "count": 3,
148        "rank": 0.05,
149        "text": "New York",
150        "timestamps": [
151          {
152            "start": 125768,
153            "end": 126034
154          },
155          {
156            "start": 171448,
157            "end": 171938
158          },
159          {
160            "start": 176008,
161            "end": 176322
162          }
163        ]
164      },
165      {
166        "count": 3,
167        "rank": 0.05,
168        "text": "climate change",
169        "timestamps": [
170          {
171            "start": 229548,
172            "end": 230230
173          },
174          {
175            "start": 244576,
176            "end": 245162
177          },
178          {
179            "start": 263348,
180            "end": 263950
181          }
182        ]
183      },
184      {
185        "count": 1,
186        "rank": 0.05,
187        "text": "Johns Hopkins University Varsity",
188        "timestamps": [
189          {
190            "start": 23972,
191            "end": 25490
192          }
193        ]
194      },
195      {
196        "count": 1,
197        "rank": 0.05,
198        "text": "heart conditions",
199        "timestamps": [
200          {
201            "start": 153988,
202            "end": 154506
203          }
204        ]
205      },
206      {
207        "count": 1,
208        "rank": 0.05,
209        "text": "air quality warnings",
210        "timestamps": [
211          {
212            "start": 12308,
213            "end": 13434
214          }
215        ]
216      }
217    ]
218  },
219  "chapters": null,
220  "confidence": 0.9404651451800253,
221  "content_safety": true,
222  "content_safety_labels": {
223    "status": "success",
224    "results": [
225      {
226        "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.",
227        "labels": [
228          {
229            "label": "disasters",
230            "confidence": 0.8142836093902588,
231            "severity": 0.4093044400215149
232          }
233        ],
234        "sentences_idx_start": 0,
235        "sentences_idx_end": 5,
236        "timestamp": {
237          "start": 250,
238          "end": 28840
239        }
240      }
241    ],
242    "summary": {
243      "disasters": 0.9940800441842205,
244      "health_issues": 0.9216489289040967
245    },
246    "severity_score_summary": {
247      "disasters": {
248        "low": 0.5733263024656846,
249        "medium": 0.42667369753431533,
250        "high": 0
251      },
252      "health_issues": {
253        "low": 0.22863814977924785,
254        "medium": 0.45014154926938227,
255        "high": 0.32122030095136983
256      }
257    }
258  },
259  "custom_spelling": null,
260  "disfluencies": false,
261  "domain": null,
262  "entities": [
263    {
264      "entity_type": "location",
265      "text": "Canada",
266      "start": 2548,
267      "end": 3130
268    },
269    {
270      "entity_type": "location",
271      "text": "the US",
272      "start": 5498,
273      "end": 6382
274    },
275    {
276      "entity_type": "location",
277      "text": "Maine",
278      "start": 7492,
279      "end": 7914
280    },
281    {
282      "entity_type": "location",
283      "text": "Maryland",
284      "start": 8212,
285      "end": 8634
286    },
287    {
288      "entity_type": "location",
289      "text": "Minnesota",
290      "start": 8932,
291      "end": 9578
292    },
293    {
294      "entity_type": "person_name",
295      "text": "Peter de Carlo",
296      "start": 18948,
297      "end": 19930
298    },
299    {
300      "entity_type": "occupation",
301      "text": "associate professor",
302      "start": 20292,
303      "end": 21194
304    },
305    {
306      "entity_type": "organization",
307      "text": "Department of Environmental Health and Engineering",
308      "start": 21508,
309      "end": 23706
310    },
311    {
312      "entity_type": "organization",
313      "text": "Johns Hopkins University Varsity",
314      "start": 23972,
315      "end": 25490
316    },
317    {
318      "entity_type": "occupation",
319      "text": "professor",
320      "start": 26076,
321      "end": 26950
322    },
323    {
324      "entity_type": "location",
325      "text": "the US",
326      "start": 45184,
327      "end": 45898
328    },
329    {
330      "entity_type": "nationality",
331      "text": "Canadian",
332      "start": 49728,
333      "end": 50086
334    }
335  ],
336  "entity_detection": true,
337  "filter_profanity": true,
338  "format_text": true,
339  "iab_categories": true,
340  "iab_categories_result": {
341    "status": "success",
342    "results": [
343      {
344        "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.",
345        "labels": [
346          {
347            "relevance": 0.988274097442627,
348            "label": "Home&Garden>IndoorEnvironmentalQuality"
349          },
350          {
351            "relevance": 0.5821335911750793,
352            "label": "NewsAndPolitics>Weather"
353          },
354          {
355            "relevance": 0.0042327106930315495,
356            "label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth"
357          },
358          {
359            "relevance": 0.0033971222583204508,
360            "label": "NewsAndPolitics>Disasters"
361          },
362          {
363            "relevance": 0.002469958271831274,
364            "label": "BusinessAndFinance>Business>GreenSolutions"
365          },
366          {
367            "relevance": 0.0014376690378412604,
368            "label": "MedicalHealth>DiseasesAndConditions>Cancer"
369          },
370          {
371            "relevance": 0.0014294233405962586,
372            "label": "Science>Environment"
373          },
374          {
375            "relevance": 0.001234519761055708,
376            "label": "Travel>TravelLocations>PolarTravel"
377          },
378          {
379            "relevance": 0.0010231725173071027,
380            "label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu"
381          },
382          {
383            "relevance": 0.0007445293595083058,
384            "label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry"
385          }
386        ],
387        "timestamp": {
388          "start": 250,
389          "end": 28840
390        }
391      }
392    ],
393    "summary": {
394      "NewsAndPolitics>Weather": 1,
395      "Home&Garden>IndoorEnvironmentalQuality": 0.9043831825256348,
396      "Science>Environment": 0.16117265820503235,
397      "BusinessAndFinance>Industries>EnvironmentalServicesIndustry": 0.14393523335456848,
398      "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth": 0.11401086300611496,
399      "BusinessAndFinance>Business>GreenSolutions": 0.06348437070846558,
400      "NewsAndPolitics>Disasters": 0.05041387677192688,
401      "Travel>TravelLocations>PolarTravel": 0.01308488193899393,
402      "HealthyLiving": 0.008222488686442375,
403      "MedicalHealth>DiseasesAndConditions>ColdAndFlu": 0.0022315620444715023,
404      "MedicalHealth>DiseasesAndConditions>HeartAndCardiovascularDiseases": 0.00213034451007843,
405      "HealthyLiving>Wellness>SmokingCessation": 0.001540527562610805,
406      "MedicalHealth>DiseasesAndConditions>Injuries": 0.0013950627762824297,
407      "BusinessAndFinance>Industries>PowerAndEnergyIndustry": 0.0012570273829624057,
408      "MedicalHealth>DiseasesAndConditions>Cancer": 0.001097781932912767,
409      "MedicalHealth>DiseasesAndConditions>Allergies": 0.0010148967849090695,
410      "MedicalHealth>DiseasesAndConditions>MentalHealth": 0.000717321818228811,
411      "Style&Fashion>PersonalCare>DeodorantAndAntiperspirant": 0.0006022014422342181,
412      "Technology&Computing>Computing>ComputerNetworking": 0.0005461975233629346,
413      "MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877
414    }
415  },
416  "language_code": "en_us",
417  "language_detection": true,
418  "multichannel": false,
419  "punctuate": true,
420  "redact_pii_audio": true,
421  "redact_pii_audio_quality": "mp3",
422  "redact_pii_policies": [
423    "us_social_security_number",
424    "credit_card_number"
425  ],
426  "redact_pii_sub": "hash",
427  "sentiment_analysis": true,
428  "sentiment_analysis_results": null,
429  "speaker_labels": true,
430  "speakers_expected": 2,
431  "speech_threshold": 0.5,
432  "remove_audio_tags": null,
433  "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.",
434  "throttled": null,
435  "utterances": [
436    {
437      "confidence": 0.9359033333333334,
438      "start": 250,
439      "end": 26950,
440      "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.",
441      "words": [
442        {
443          "confidence": 0.97503,
444          "start": 250,
445          "end": 650,
446          "text": "Smoke",
447          "speaker": "A"
448        },
449        {
450          "confidence": 0.99999,
451          "start": 730,
452          "end": 1022,
453          "text": "from",
454          "speaker": "A"
455        },
456        {
457          "confidence": 0.99843,
458          "start": 1076,
459          "end": 1418,
460          "text": "hundreds",
461          "speaker": "A"
462        },
463        {
464          "confidence": 0.85,
465          "start": 1434,
466          "end": 1614,
467          "text": "of",
468          "speaker": "A"
469        },
470        {
471          "confidence": 0.89657,
472          "start": 1652,
473          "end": 2346,
474          "text": "wildfires",
475          "speaker": "A"
476        },
477        {
478          "confidence": 0.99994,
479          "start": 2378,
480          "end": 2526,
481          "text": "in",
482          "speaker": "A"
483        },
484        {
485          "confidence": 0.93864,
486          "start": 2548,
487          "end": 3130,
488          "text": "Canada",
489          "speaker": "A"
490        },
491        {
492          "confidence": 0.999,
493          "start": 3210,
494          "end": 3454,
495          "text": "is",
496          "speaker": "A"
497        },
498        {
499          "confidence": 0.75366,
500          "start": 3492,
501          "end": 3946,
502          "text": "triggering",
503          "speaker": "A"
504        },
505        {
506          "confidence": 1,
507          "start": 3978,
508          "end": 4174,
509          "text": "air",
510          "speaker": "A"
511        },
512        {
513          "confidence": 0.87745,
514          "start": 4212,
515          "end": 4558,
516          "text": "quality",
517          "speaker": "A"
518        },
519        {
520          "confidence": 0.94739,
521          "start": 4644,
522          "end": 5114,
523          "text": "alerts",
524          "speaker": "A"
525        },
526        {
527          "confidence": 0.99726,
528          "start": 5162,
529          "end": 5466,
530          "text": "throughout",
531          "speaker": "A"
532        },
533        {
534          "confidence": 0.79,
535          "start": 5498,
536          "end": 5694,
537          "text": "the",
538          "speaker": "A"
539        },
540        {
541          "confidence": 0.88,
542          "start": 5732,
543          "end": 6382,
544          "text": "US.",
545          "speaker": "A"
546        }
547      ],
548      "speaker": "A"
549    }
550  ],
551  "webhook_auth_header_name": "webhook-secret",
552  "webhook_status_code": 200,
553  "webhook_url": "https://your-webhook-url.tld/path",
554  "words": [
555    {
556      "confidence": 0.97465,
557      "start": 250,
558      "end": 650,
559      "text": "Smoke",
560      "speaker": null
561    },
562    {
563      "confidence": 0.99999,
564      "start": 730,
565      "end": 1022,
566      "text": "from",
567      "speaker": null
568    },
569    {
570      "confidence": 0.99844,
571      "start": 1076,
572      "end": 1418,
573      "text": "hundreds",
574      "speaker": null
575    },
576    {
577      "confidence": 0.84,
578      "start": 1434,
579      "end": 1614,
580      "text": "of",
581      "speaker": null
582    },
583    {
584      "confidence": 0.89572,
585      "start": 1652,
586      "end": 2346,
587      "text": "wildfires",
588      "speaker": null
589    },
590    {
591      "confidence": 0.99994,
592      "start": 2378,
593      "end": 2526,
594      "text": "in",
595      "speaker": null
596    },
597    {
598      "confidence": 0.93953,
599      "start": 2548,
600      "end": 3130,
601      "text": "Canada",
602      "speaker": null
603    },
604    {
605      "confidence": 0.999,
606      "start": 3210,
607      "end": 3454,
608      "text": "is",
609      "speaker": null
610    },
611    {
612      "confidence": 0.74794,
613      "start": 3492,
614      "end": 3946,
615      "text": "triggering",
616      "speaker": null
617    },
618    {
619      "confidence": 1,
620      "start": 3978,
621      "end": 4174,
622      "text": "air",
623      "speaker": null
624    },
625    {
626      "confidence": 0.88077,
627      "start": 4212,
628      "end": 4558,
629      "text": "quality",
630      "speaker": null
631    },
632    {
633      "confidence": 0.94814,
634      "start": 4644,
635      "end": 5114,
636      "text": "alerts",
637      "speaker": null
638    },
639    {
640      "confidence": 0.99726,
641      "start": 5162,
642      "end": 5466,
643      "text": "throughout",
644      "speaker": null
645    },
646    {
647      "confidence": 0.79,
648      "start": 5498,
649      "end": 5694,
650      "text": "the",
651      "speaker": null
652    },
653    {
654      "confidence": 0.89,
655      "start": 5732,
656      "end": 6382,
657      "text": "US.",
658      "speaker": null
659    }
660  ],
661  "auto_chapters": false,
662  "summary": null,
663  "summary_model": null,
664  "summary_type": null,
665  "custom_topics": true,
666  "topics": []
667}
<llms-only> > For the complete documentation index, see [llms.txt](https://www.assemblyai.com/docs/llms.txt) </llms-only> <Note>To retrieve your transcriptions on our EU server, replace `api.assemblyai.com` with `api.eu.assemblyai.com`.</Note> Get the transcript resource. The transcript is ready when the "status" is "completed".
Was this page helpful?
Previous

Get sentences in transcript

Next
Built with

To retrieve your transcriptions on our EU server, replace api.assemblyai.com with api.eu.assemblyai.com.
Get the transcript resource. The transcript is ready when the “status” is “completed”.

Authentication

Authorizationstring
API Key authentication via header

Path parameters

transcript_idstringRequired
ID of the transcript

Response

The transcript resource
audio_urlstringformat: "url"
The URL of the media that was transcribed
auto_highlightsboolean

Whether Key Phrases is enabled, either true or false

idstringformat: "uuid"
The unique identifier of your transcript
language_confidencedouble or null0-1

The confidence score for the detected language, between 0.0 (low confidence) and 1.0 (high confidence). See Automatic Language Detection for more details.

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. See Automatic Language Detection for more details.

redact_piiboolean

Whether PII Redaction is enabled, either true or false

statusenum
The status of your transcript. Possible values are queued, processing, completed, or error.
Allowed values:
webhook_authboolean

Whether webhook authentication details were provided

summarizationbooleanDeprecated

Whether Summarization is enabled, either true or false. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.

Note: This parameter is only supported for the Universal-2 model.

acoustic_modelstringDeprecated
This parameter does not currently have any functionality attached to it.
language_modelstringDeprecated
This parameter does not currently have any functionality attached to it.
speech_modelstring or nullDeprecated

This parameter has been replaced with the speech_models parameter, learn more about the speech_models parameter here.

audio_channelsinteger

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

audio_durationinteger or null
The duration of this transcript object's media file, in seconds
audio_end_atinteger or null

The point in time, in milliseconds, in the file at which the transcription was terminated. See Set the start and end of the transcript for more details.

audio_start_frominteger or null

The point in time, in milliseconds, in the file at which the transcription was started. See Set the start and end of the transcript for more details.

auto_highlights_resultobject or null

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

chapterslist of objects or null

An array of temporally sequential chapters for the audio file. See Auto Chapters for more information.

confidencedouble or null0-1

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

content_safetyboolean or null

Whether 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.

custom_spellinglist of objects or null

Customize how words are spelled and formatted using to and from values. See Custom Spelling for more details.

disfluenciesboolean or null

Transcribe Filler Words, like “umm”, in your media file; can be true or false. Supported on Universal-3 Pro and Universal-2.

domainstring or null

The domain-specific model applied to the transcript. When set to "medical-v1", Medical Mode was used to improve accuracy for medical terminology.

entitieslist of objects or null

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

entity_detectionboolean or null

Whether Entity Detection is enabled, can be true or false

errorstring
Error message of why the transcript failed
filter_profanityboolean or null

Whether Profanity Filtering is enabled, either true or false

format_textboolean or null

Whether Text Formatting is enabled, either true or false

iab_categoriesboolean or null

Whether 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.

keyterms_promptlist of strings

Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See Keyterms Prompting for more details.

language_codeenum

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

language_codeslist of enums or null

The language codes of your audio file. Used for Code switching One of the values specified must be en.

language_detectionboolean or null

Whether Automatic language detection is enabled, either true or false

language_detection_optionsobject

Specify options for Automatic Language Detection.

multichannelboolean or null

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

promptstring

Provide natural language prompting of up to 1,500 words of contextual information to the model. See the Prompting Guide for best practices.

Note: This parameter is only supported for the Universal-3 Pro model.

punctuateboolean or null

Whether Automatic Punctuation 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.

redact_pii_audio_optionsobject

The options for PII-redacted audio, if redact_pii_audio is enabled. See 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.

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.

redact_pii_subenum

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

Allowed values:
redact_pii_return_unredactedboolean or null

Whether the original unredacted transcript was also returned alongside the redacted one. When true, the response includes unredacted_text, unredacted_words, and unredacted_utterances. See PII redaction for more information.

sentiment_analysisboolean or null

Whether 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.

speaker_labelsboolean or null

Whether 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 Set number of speakers expected for more details.

speech_model_usedstring

The speech model that was actually used for the transcription. See Model Selection for available models.

speech_modelslist of strings or null

List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. See Model Selection for available models and routing behavior.

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. See Speech Threshold for more details.

speech_understandingobject

Speech understanding tasks like Translation, Speaker Identification, and Custom Formatting. See the task-specific docs for available options and configuration.

remove_audio_tagsenum or null

Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to "all" to remove all inline annotations, or "speaker" to remove only speaker cues while keeping other annotations.

Note: This parameter is only supported for the Universal-3 Pro model.

Allowed values:
temperaturedouble or null0-1

The temperature that was used for the model’s response. See the Prompting Guide for more details.

Note: This parameter can only be used with the Universal-3 Pro model.

textstring or null
The textual transcript of your media file
unredacted_textstring or null

The original textual transcript of your media file before PII redaction was applied. Only returned when redact_pii_return_unredacted was set to true on the transcription request, otherwise this field is omitted and the text field remains fully redacted. See PII redaction for more information.

throttledboolean or null
True while a request is throttled and false when a request is no longer throttled
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.

unredacted_utteranceslist of objects or null

The original turn-by-turn utterance objects before PII redaction was applied. Same shape as utterances. Only returned when redact_pii_return_unredacted was set to true on the transcription request, otherwise this field is omitted and the utterances field remains fully redacted. See PII redaction for more information.

webhook_auth_header_namestring or null

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

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_urlstring or nullformat: "url"

The URL to which we send webhook requests.

wordslist of objects or null

An array of temporally-sequential word objects, one for each word in the transcript.

unredacted_wordslist of objects or null

The original temporally-sequential word objects before PII redaction was applied. Same shape as words. Only returned when redact_pii_return_unredacted was set to true on the transcription request, otherwise this field is omitted and the words field remains fully redacted. See PII redaction for more information.

translated_textsobject

Translated text keyed by language code. See Translation for more details.

auto_chaptersboolean or nullDeprecated

Whether Auto Chapters is enabled, can be true or false. Deprecated - use LLM Gateway instead for more flexible chapter summaries. See the updated Auto Chapters page for details.

Note: This parameter is only supported for the Universal-2 model.

summarystring or nullDeprecated

The generated summary of the media file, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.

summary_modelstring or nullDeprecated

The Summarization model used to generate the summary, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.

summary_typestring or nullDeprecated

The type of summary generated, if Summarization is enabled. Deprecated - use LLM Gateway instead for more flexible summaries. See the updated Summarization page for details.

custom_topicsboolean or nullDeprecated
This parameter does not currently have any functionality attached to it.
speed_boostboolean or nullDeprecated
This parameter does not currently have any functionality attached to it.
topicslist of stringsDeprecated
This parameter does not currently have any functionality attached to it.

Errors

400
Bad Request Error
401
Unauthorized Error
404
Not Found Error
429
Too Many Requests Error
500
Internal Server Error
503
Service Unavailable Error
504
Gateway Timeout Error