Transcribe audio — AssemblyAI

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

Request

This endpoint expects an object.

audio_urlstringRequired

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_chaptersbooleanOptional

Enable Auto Chapters, can be true or false

auto_highlightsbooleanOptional

Enable Key Phrases, either true or false

boost_paramenumOptional

Allowed values: lowdefaulthigh

How much to boost specified words

content_safetybooleanOptional

Enable Content Moderation, can be true or false

content_safety_confidenceintegerOptional>=25<=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

custom_topicsbooleanOptional

Enable custom topics, either true or false

disfluenciesbooleanOptional

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

entity_detectionbooleanOptional

Enable Entity Detection, can be true or false

filter_profanitybooleanOptional

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

format_textbooleanOptional

Enable Text Formatting, can be true or false

iab_categoriesbooleanOptional

Enable Topic Detection, can be true or false

language_codeenumOptional

The language of your audio file. Possible values are found in 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_detectionbooleanOptional

Enable Automatic language detection, either true or false.

multichannelbooleanOptional

Enable Multichannel transcription, can be true or false.

punctuatebooleanOptional

Enable Automatic Punctuation, can be true or false

redact_piibooleanOptional

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

redact_pii_audiobooleanOptional

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

redact_pii_audio_quality"mp3" or "wav"Optional

Allowed values: mp3wav

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

redact_pii_policieslist of enumsOptional

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

redact_pii_sub"entity_name" or "hash"Optional

Allowed values: entity_namehash

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

sentiment_analysisbooleanOptional

Enable Sentiment Analysis, can be true or false

speaker_labelsbooleanOptional

Enable Speaker diarization, can be true or false

speakers_expectedintegerOptional

Tells the speaker label model how many speakers it should attempt to identify, up to 10. See Speaker diarization for more details.

speech_model"best" or "nano"Optional

Allowed values: bestnano

The speech model to use for the transcription.

speech_thresholddoubleOptional

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

summarizationbooleanOptional

Enable Summarization, can be true or false

summary_modelenumOptional

Allowed values: informativeconversationalcatchy

The model to summarize the transcript

summary_typeenumOptional

Allowed values: bulletsbullets_verbosegistheadlineparagraph

The type of summary

topicslist of stringsOptional

The list of custom topics

webhook_auth_header_namestringOptional

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

webhook_auth_header_valuestringOptional

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

webhook_urlstringOptional

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.

word_boostlist of stringsOptional

The list of custom vocabulary to boost transcription probability for

dual_channelbooleanOptionalDeprecated

Enable Dual Channel transcription, can be true or false.

Response

This endpoint returns an object.

idstring

The unique identifier of your transcript

audio_urlstring

The URL of the media that was transcribed

statusenum

Allowed values: queuedprocessingcompletederror

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

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

summarizationboolean

Whether 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_codeenumOptional

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

language_detectionbooleanOptional

Whether Automatic language detection is enabled, either true or false

language_confidence_thresholddoubleOptional

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

language_confidencedoubleOptional>=0<=1

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

speech_model"best" or "nano"Optional

Allowed values: bestnano

The speech model to use for the transcription.

textstringOptional

The textual transcript of your media file

wordslist of objectsOptional

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

utteranceslist of objectsOptional

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

confidencedoubleOptional>=0<=1

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

audio_durationintegerOptional

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

punctuatebooleanOptional

Whether Automatic Punctuation is enabled, either true or false

format_textbooleanOptional

Whether Text Formatting is enabled, either true or false

disfluenciesbooleanOptional

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

multichannelbooleanOptional

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

audio_channelsintegerOptional

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

webhook_urlstringOptional

webhook_status_codeintegerOptional

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_namestringOptional

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

auto_highlights_resultobjectOptional

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

audio_start_fromintegerOptional

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

audio_end_atintegerOptional

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

word_boostlist of stringsOptional

The list of custom vocabulary to boost transcription probability for

boost_paramstringOptional

The word boost parameter value

filter_profanitybooleanOptional

Whether Profanity Filtering is enabled, either true or false

redact_pii_audiobooleanOptional

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

redact_pii_audio_quality"mp3" or "wav"Optional

Allowed values: mp3wav

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

redact_pii_policieslist of enumsOptional

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

redact_pii_sub"entity_name" or "hash"Optional

Allowed values: entity_namehash

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

speaker_labelsbooleanOptional

Whether Speaker diarization is enabled, can be true or false

speakers_expectedintegerOptional

Tell the speaker label model how many speakers it should attempt to identify, up to 10. See Speaker diarization for more details.

content_safetybooleanOptional

Whether Content Moderation is enabled, can be true or false

content_safety_labelsobjectOptional

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

iab_categoriesbooleanOptional

Whether Topic Detection is enabled, can be true or false

iab_categories_resultobjectOptional

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

custom_spellinglist of objectsOptional

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

auto_chaptersbooleanOptional

Whether Auto Chapters is enabled, can be true or false

chapterslist of objectsOptional

An array of temporally sequential chapters for the audio file

summary_typestringOptional

The type of summary generated, if Summarization is enabled

summary_modelstringOptional

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

summarystringOptional

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

custom_topicsbooleanOptional

Whether custom topics is enabled, either true or false

topicslist of stringsOptional

The list of custom topics provided if custom topics is enabled

sentiment_analysisbooleanOptional

Whether Sentiment Analysis is enabled, can be true or false

sentiment_analysis_resultslist of objectsOptional

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

entity_detectionbooleanOptional

Whether Entity Detection is enabled, can be true or false

entitieslist of objectsOptional

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

speech_thresholddoubleOptional

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

throttledbooleanOptional

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

errorstringOptional

Error message of why the transcript failed

dual_channelbooleanOptionalDeprecated

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

speed_boostbooleanOptionalDeprecated

Whether speed boost is enabled

Errors

1 curl -X POST https://api.assemblyai.com/v2/transcript \ 2 -H "Authorization: <apiKey>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "audio_url": "https://assembly.ai/wildfires.mp3", 6 "audio_end_at": 280, 7 "audio_start_from": 10, 8 "auto_chapters": true, 9 "auto_highlights": true, 10 "boost_param": "high", 11 "content_safety": true, 12 "custom_spelling": [ 13 { 14 "from": [ 15 "dicarlo" 16 ], 17 "to": "Decarlo" 18 } 19 ], 20 "custom_topics": true, 21 "disfluencies": false, 22 "entity_detection": true, 23 "filter_profanity": true, 24 "format_text": true, 25 "iab_categories": true, 26 "language_code": "en_us", 27 "language_confidence_threshold": 0.7, 28 "language_detection": true, 29 "multichannel": true, 30 "punctuate": true, 31 "redact_pii": true, 32 "redact_pii_audio": true, 33 "redact_pii_audio_quality": "mp3", 34 "redact_pii_policies": [ 35 "us_social_security_number", 36 "credit_card_number" 37 ], 38 "redact_pii_sub": "hash", 39 "sentiment_analysis": true, 40 "speaker_labels": true, 41 "speakers_expected": 2, 42 "speech_threshold": 0.5, 43 "summarization": true, 44 "summary_model": "informative", 45 "summary_type": "bullets", 46 "topics": [ 47 "topics" 48 ], 49 "webhook_auth_header_name": "webhook-secret", 50 "webhook_auth_header_value": "webhook-secret-value", 51 "webhook_url": "https://your-webhook-url/path", 52 "word_boost": [ 53 "aws", 54 "azure", 55 "google cloud" 56 ], 57 "dual_channel": false 58 }'

1 { 2 "id": "9ea68fd3-f953-42c1-9742-976c447fb463", 3 "audio_url": "https://assembly.ai/wildfires.mp3", 4 "status": "completed", 5 "webhook_auth": true, 6 "auto_highlights": true, 7 "redact_pii": true, 8 "summarization": true, 9 "language_model": "assemblyai_default", 10 "acoustic_model": "assemblyai_default", 11 "language_code": "en_us", 12 "language_detection": true, 13 "language_confidence_threshold": 0.7, 14 "language_confidence": 0.9959, 15 "speech_model": "best", 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 "channel": "channel", 24 "speaker": "speaker" 25 }, 26 { 27 "confidence": 0.99999, 28 "start": 730, 29 "end": 1022, 30 "text": "from", 31 "channel": "channel", 32 "speaker": "speaker" 33 }, 34 { 35 "confidence": 0.99844, 36 "start": 1076, 37 "end": 1418, 38 "text": "hundreds", 39 "channel": "channel", 40 "speaker": "speaker" 41 }, 42 { 43 "confidence": 0.84, 44 "start": 1434, 45 "end": 1614, 46 "text": "of", 47 "channel": "channel", 48 "speaker": "speaker" 49 }, 50 { 51 "confidence": 0.89572, 52 "start": 1652, 53 "end": 2346, 54 "text": "wildfires", 55 "channel": "channel", 56 "speaker": "speaker" 57 }, 58 { 59 "confidence": 0.99994, 60 "start": 2378, 61 "end": 2526, 62 "text": "in", 63 "channel": "channel", 64 "speaker": "speaker" 65 }, 66 { 67 "confidence": 0.93953, 68 "start": 2548, 69 "end": 3130, 70 "text": "Canada", 71 "channel": "channel", 72 "speaker": "speaker" 73 }, 74 { 75 "confidence": 0.999, 76 "start": 3210, 77 "end": 3454, 78 "text": "is", 79 "channel": "channel", 80 "speaker": "speaker" 81 }, 82 { 83 "confidence": 0.74794, 84 "start": 3492, 85 "end": 3946, 86 "text": "triggering", 87 "channel": "channel", 88 "speaker": "speaker" 89 }, 90 { 91 "confidence": 1, 92 "start": 3978, 93 "end": 4174, 94 "text": "air", 95 "channel": "channel", 96 "speaker": "speaker" 97 }, 98 { 99 "confidence": 0.88077, 100 "start": 4212, 101 "end": 4558, 102 "text": "quality", 103 "channel": "channel", 104 "speaker": "speaker" 105 }, 106 { 107 "confidence": 0.94814, 108 "start": 4644, 109 "end": 5114, 110 "text": "alerts", 111 "channel": "channel", 112 "speaker": "speaker" 113 }, 114 { 115 "confidence": 0.99726, 116 "start": 5162, 117 "end": 5466, 118 "text": "throughout", 119 "channel": "channel", 120 "speaker": "speaker" 121 }, 122 { 123 "confidence": 0.79, 124 "start": 5498, 125 "end": 5694, 126 "text": "the", 127 "channel": "channel", 128 "speaker": "speaker" 129 }, 130 { 131 "confidence": 0.89, 132 "start": 5732, 133 "end": 6382, 134 "text": "US.", 135 "channel": "channel", 136 "speaker": "speaker" 137 } 138 ], 139 "utterances": [ 140 { 141 "confidence": 0.9359033333333334, 142 "start": 250, 143 "end": 26950, 144 "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.", 145 "words": [ 146 { 147 "confidence": 0.97503, 148 "start": 250, 149 "end": 650, 150 "text": "Smoke", 151 "speaker": "A" 152 }, 153 { 154 "confidence": 0.99999, 155 "start": 730, 156 "end": 1022, 157 "text": "from", 158 "speaker": "A" 159 }, 160 { 161 "confidence": 0.99843, 162 "start": 1076, 163 "end": 1418, 164 "text": "hundreds", 165 "speaker": "A" 166 }, 167 { 168 "confidence": 0.85, 169 "start": 1434, 170 "end": 1614, 171 "text": "of", 172 "speaker": "A" 173 }, 174 { 175 "confidence": 0.89657, 176 "start": 1652, 177 "end": 2346, 178 "text": "wildfires", 179 "speaker": "A" 180 }, 181 { 182 "confidence": 0.99994, 183 "start": 2378, 184 "end": 2526, 185 "text": "in", 186 "speaker": "A" 187 }, 188 { 189 "confidence": 0.93864, 190 "start": 2548, 191 "end": 3130, 192 "text": "Canada", 193 "speaker": "A" 194 }, 195 { 196 "confidence": 0.999, 197 "start": 3210, 198 "end": 3454, 199 "text": "is", 200 "speaker": "A" 201 }, 202 { 203 "confidence": 0.75366, 204 "start": 3492, 205 "end": 3946, 206 "text": "triggering", 207 "speaker": "A" 208 }, 209 { 210 "confidence": 1, 211 "start": 3978, 212 "end": 4174, 213 "text": "air", 214 "speaker": "A" 215 }, 216 { 217 "confidence": 0.87745, 218 "start": 4212, 219 "end": 4558, 220 "text": "quality", 221 "speaker": "A" 222 }, 223 { 224 "confidence": 0.94739, 225 "start": 4644, 226 "end": 5114, 227 "text": "alerts", 228 "speaker": "A" 229 }, 230 { 231 "confidence": 0.99726, 232 "start": 5162, 233 "end": 5466, 234 "text": "throughout", 235 "speaker": "A" 236 }, 237 { 238 "confidence": 0.79, 239 "start": 5498, 240 "end": 5694, 241 "text": "the", 242 "speaker": "A" 243 }, 244 { 245 "confidence": 0.88, 246 "start": 5732, 247 "end": 6382, 248 "text": "US.", 249 "speaker": "A" 250 } 251 ], 252 "speaker": "A", 253 "channel": "channel" 254 } 255 ], 256 "confidence": 0.9404651451800253, 257 "audio_duration": 281, 258 "punctuate": true, 259 "format_text": true, 260 "disfluencies": false, 261 "multichannel": false, 262 "audio_channels": 1, 263 "webhook_url": "https://your-webhook-url.tld/path", 264 "webhook_status_code": 200, 265 "webhook_auth_header_name": "webhook-secret", 266 "auto_highlights_result": { 267 "status": "success", 268 "results": [ 269 { 270 "count": 1, 271 "rank": 0.08, 272 "text": "air quality alerts", 273 "timestamps": [ 274 { 275 "start": 3978, 276 "end": 5114 277 } 278 ] 279 }, 280 { 281 "count": 1, 282 "rank": 0.08, 283 "text": "wide ranging air quality consequences", 284 "timestamps": [ 285 { 286 "start": 235388, 287 "end": 238694 288 } 289 ] 290 }, 291 { 292 "count": 1, 293 "rank": 0.07, 294 "text": "more wildfires", 295 "timestamps": [ 296 { 297 "start": 230972, 298 "end": 232354 299 } 300 ] 301 }, 302 { 303 "count": 1, 304 "rank": 0.07, 305 "text": "air pollution", 306 "timestamps": [ 307 { 308 "start": 156004, 309 "end": 156910 310 } 311 ] 312 }, 313 { 314 "count": 3, 315 "rank": 0.07, 316 "text": "weather systems", 317 "timestamps": [ 318 { 319 "start": 47344, 320 "end": 47958 321 }, 322 { 323 "start": 205268, 324 "end": 205818 325 }, 326 { 327 "start": 211588, 328 "end": 213434 329 } 330 ] 331 }, 332 { 333 "count": 2, 334 "rank": 0.06, 335 "text": "high levels", 336 "timestamps": [ 337 { 338 "start": 121128, 339 "end": 121646 340 }, 341 { 342 "start": 155412, 343 "end": 155866 344 } 345 ] 346 }, 347 { 348 "count": 1, 349 "rank": 0.06, 350 "text": "health conditions", 351 "timestamps": [ 352 { 353 "start": 152138, 354 "end": 152666 355 } 356 ] 357 }, 358 { 359 "count": 2, 360 "rank": 0.06, 361 "text": "Peter de Carlo", 362 "timestamps": [ 363 { 364 "start": 18948, 365 "end": 19930 366 }, 367 { 368 "start": 268298, 369 "end": 269194 370 } 371 ] 372 }, 373 { 374 "count": 1, 375 "rank": 0.06, 376 "text": "New York City", 377 "timestamps": [ 378 { 379 "start": 125768, 380 "end": 126274 381 } 382 ] 383 }, 384 { 385 "count": 1, 386 "rank": 0.05, 387 "text": "respiratory conditions", 388 "timestamps": [ 389 { 390 "start": 152964, 391 "end": 153786 392 } 393 ] 394 }, 395 { 396 "count": 3, 397 "rank": 0.05, 398 "text": "New York", 399 "timestamps": [ 400 { 401 "start": 125768, 402 "end": 126034 403 }, 404 { 405 "start": 171448, 406 "end": 171938 407 }, 408 { 409 "start": 176008, 410 "end": 176322 411 } 412 ] 413 }, 414 { 415 "count": 3, 416 "rank": 0.05, 417 "text": "climate change", 418 "timestamps": [ 419 { 420 "start": 229548, 421 "end": 230230 422 }, 423 { 424 "start": 244576, 425 "end": 245162 426 }, 427 { 428 "start": 263348, 429 "end": 263950 430 } 431 ] 432 }, 433 { 434 "count": 1, 435 "rank": 0.05, 436 "text": "Johns Hopkins University Varsity", 437 "timestamps": [ 438 { 439 "start": 23972, 440 "end": 25490 441 } 442 ] 443 }, 444 { 445 "count": 1, 446 "rank": 0.05, 447 "text": "heart conditions", 448 "timestamps": [ 449 { 450 "start": 153988, 451 "end": 154506 452 } 453 ] 454 }, 455 { 456 "count": 1, 457 "rank": 0.05, 458 "text": "air quality warnings", 459 "timestamps": [ 460 { 461 "start": 12308, 462 "end": 13434 463 } 464 ] 465 } 466 ] 467 }, 468 "audio_start_from": 10, 469 "audio_end_at": 280, 470 "word_boost": [ 471 "aws", 472 "azure", 473 "google cloud" 474 ], 475 "boost_param": "high", 476 "filter_profanity": true, 477 "redact_pii_audio": true, 478 "redact_pii_audio_quality": "mp3", 479 "redact_pii_policies": [ 480 "us_social_security_number", 481 "credit_card_number" 482 ], 483 "redact_pii_sub": "hash", 484 "speaker_labels": true, 485 "speakers_expected": 2, 486 "content_safety": true, 487 "content_safety_labels": { 488 "status": "success", 489 "results": [ 490 { 491 "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.", 492 "labels": [ 493 { 494 "label": "disasters", 495 "confidence": 0.8142836093902588, 496 "severity": 0.4093044400215149 497 } 498 ], 499 "sentences_idx_start": 0, 500 "sentences_idx_end": 5, 501 "timestamp": { 502 "start": 250, 503 "end": 28840 504 } 505 } 506 ], 507 "summary": { 508 "disasters": 0.9940800441842205, 509 "health_issues": 0.9216489289040967 510 }, 511 "severity_score_summary": { 512 "disasters": { 513 "low": 0.5733263024656846, 514 "medium": 0.42667369753431533, 515 "high": 0 516 }, 517 "health_issues": { 518 "low": 0.22863814977924785, 519 "medium": 0.45014154926938227, 520 "high": 0.32122030095136983 521 } 522 } 523 }, 524 "iab_categories": true, 525 "iab_categories_result": { 526 "status": "success", 527 "results": [ 528 { 529 "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.", 530 "labels": [ 531 { 532 "relevance": 0.988274097442627, 533 "label": "Home&Garden>IndoorEnvironmentalQuality" 534 }, 535 { 536 "relevance": 0.5821335911750793, 537 "label": "NewsAndPolitics>Weather" 538 }, 539 { 540 "relevance": 0.0042327106930315495, 541 "label": "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth" 542 }, 543 { 544 "relevance": 0.0033971222583204508, 545 "label": "NewsAndPolitics>Disasters" 546 }, 547 { 548 "relevance": 0.002469958271831274, 549 "label": "BusinessAndFinance>Business>GreenSolutions" 550 }, 551 { 552 "relevance": 0.0014376690378412604, 553 "label": "MedicalHealth>DiseasesAndConditions>Cancer" 554 }, 555 { 556 "relevance": 0.0014294233405962586, 557 "label": "Science>Environment" 558 }, 559 { 560 "relevance": 0.001234519761055708, 561 "label": "Travel>TravelLocations>PolarTravel" 562 }, 563 { 564 "relevance": 0.0010231725173071027, 565 "label": "MedicalHealth>DiseasesAndConditions>ColdAndFlu" 566 }, 567 { 568 "relevance": 0.0007445293595083058, 569 "label": "BusinessAndFinance>Industries>PowerAndEnergyIndustry" 570 } 571 ], 572 "timestamp": { 573 "start": 250, 574 "end": 28840 575 } 576 } 577 ], 578 "summary": { 579 "NewsAndPolitics>Weather": 1, 580 "Home&Garden>IndoorEnvironmentalQuality": 0.9043831825256348, 581 "Science>Environment": 0.16117265820503235, 582 "BusinessAndFinance>Industries>EnvironmentalServicesIndustry": 0.14393523335456848, 583 "MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth": 0.11401086300611496, 584 "BusinessAndFinance>Business>GreenSolutions": 0.06348437070846558, 585 "NewsAndPolitics>Disasters": 0.05041387677192688, 586 "Travel>TravelLocations>PolarTravel": 0.01308488193899393, 587 "HealthyLiving": 0.008222488686442375, 588 "MedicalHealth>DiseasesAndConditions>ColdAndFlu": 0.0022315620444715023, 589 "MedicalHealth>DiseasesAndConditions>HeartAndCardiovascularDiseases": 0.00213034451007843, 590 "HealthyLiving>Wellness>SmokingCessation": 0.001540527562610805, 591 "MedicalHealth>DiseasesAndConditions>Injuries": 0.0013950627762824297, 592 "BusinessAndFinance>Industries>PowerAndEnergyIndustry": 0.0012570273829624057, 593 "MedicalHealth>DiseasesAndConditions>Cancer": 0.001097781932912767, 594 "MedicalHealth>DiseasesAndConditions>Allergies": 0.0010148967849090695, 595 "MedicalHealth>DiseasesAndConditions>MentalHealth": 0.000717321818228811, 596 "Style&Fashion>PersonalCare>DeodorantAndAntiperspirant": 0.0006022014422342181, 597 "Technology&Computing>Computing>ComputerNetworking": 0.0005461975233629346, 598 "MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877 599 } 600 }, 601 "custom_spelling": [ 602 { 603 "from": [ 604 "dicarlo" 605 ], 606 "to": "Decarlo" 607 } 608 ], 609 "auto_chapters": true, 610 "chapters": [ 611 { 612 "gist": "Smoggy air quality alerts across US", 613 "headline": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts across US", 614 "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.", 615 "start": 250, 616 "end": 28840 617 }, 618 { 619 "gist": "What is it about the conditions right now that have caused this round", 620 "headline": "High particulate matter in wildfire smoke can lead to serious health problems", 621 "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?", 622 "start": 29610, 623 "end": 280340 624 } 625 ], 626 "summary_type": "bullets", 627 "summary_model": "informative", 628 "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?", 629 "custom_topics": true, 630 "topics": [ 631 "topics" 632 ], 633 "sentiment_analysis": true, 634 "sentiment_analysis_results": [ 635 { 636 "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US.", 637 "start": 250, 638 "end": 6350, 639 "sentiment": "NEGATIVE", 640 "confidence": 0.8181032538414001, 641 "channel": "channel", 642 "speaker": "speaker" 643 } 644 ], 645 "entity_detection": true, 646 "entities": [ 647 { 648 "entity_type": "location", 649 "text": "Canada", 650 "start": 2548, 651 "end": 3130 652 }, 653 { 654 "entity_type": "location", 655 "text": "the US", 656 "start": 5498, 657 "end": 6382 658 }, 659 { 660 "entity_type": "location", 661 "text": "Maine", 662 "start": 7492, 663 "end": 7914 664 }, 665 { 666 "entity_type": "location", 667 "text": "Maryland", 668 "start": 8212, 669 "end": 8634 670 }, 671 { 672 "entity_type": "location", 673 "text": "Minnesota", 674 "start": 8932, 675 "end": 9578 676 }, 677 { 678 "entity_type": "person_name", 679 "text": "Peter de Carlo", 680 "start": 18948, 681 "end": 19930 682 }, 683 { 684 "entity_type": "occupation", 685 "text": "associate professor", 686 "start": 20292, 687 "end": 21194 688 }, 689 { 690 "entity_type": "organization", 691 "text": "Department of Environmental Health and Engineering", 692 "start": 21508, 693 "end": 23706 694 }, 695 { 696 "entity_type": "organization", 697 "text": "Johns Hopkins University Varsity", 698 "start": 23972, 699 "end": 25490 700 }, 701 { 702 "entity_type": "occupation", 703 "text": "professor", 704 "start": 26076, 705 "end": 26950 706 }, 707 { 708 "entity_type": "location", 709 "text": "the US", 710 "start": 45184, 711 "end": 45898 712 }, 713 { 714 "entity_type": "nationality", 715 "text": "Canadian", 716 "start": 49728, 717 "end": 50086 718 } 719 ], 720 "speech_threshold": 0.5, 721 "throttled": true, 722 "error": "error", 723 "dual_channel": false, 724 "speed_boost": true 725 }

1	curl -X POST https://api.assemblyai.com/v2/transcript \
2	-H "Authorization: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"audio_url": "https://assembly.ai/wildfires.mp3",
6	"audio_end_at": 280,
7	"audio_start_from": 10,
8	"auto_chapters": true,
9	"auto_highlights": true,
10	"boost_param": "high",
11	"content_safety": true,
12	"custom_spelling": [
13	{
14	"from": [
15	"dicarlo"
16	],
17	"to": "Decarlo"
18	}
19	],
20	"custom_topics": true,
21	"disfluencies": false,
22	"entity_detection": true,
23	"filter_profanity": true,
24	"format_text": true,
25	"iab_categories": true,
26	"language_code": "en_us",
27	"language_confidence_threshold": 0.7,
28	"language_detection": true,
29	"multichannel": true,
30	"punctuate": true,
31	"redact_pii": true,
32	"redact_pii_audio": true,
33	"redact_pii_audio_quality": "mp3",
34	"redact_pii_policies": [
35	"us_social_security_number",
36	"credit_card_number"
37	],
38	"redact_pii_sub": "hash",
39	"sentiment_analysis": true,
40	"speaker_labels": true,
41	"speakers_expected": 2,
42	"speech_threshold": 0.5,
43	"summarization": true,
44	"summary_model": "informative",
45	"summary_type": "bullets",
46	"topics": [
47	"topics"
48	],
49	"webhook_auth_header_name": "webhook-secret",
50	"webhook_auth_header_value": "webhook-secret-value",
51	"webhook_url": "https://your-webhook-url/path",
52	"word_boost": [
53	"aws",
54	"azure",
55	"google cloud"
56	],
57	"dual_channel": false
58	}'