GET
/v1/schemas/assemblyai/audio/v2/transcript
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace874d4c159d3adf6be986438d01502246300297a346fc7a7630753ff1e9ac38f3{
"fetchedAt": 1794460215,
"extractorVersion": "2",
"verifiedAt": null
} |
Request body
0 properties · 0 required · 0 $defsThis schema isn’t a plain object with properties — showing the raw JSON instead.
application/json
{
"provider": "assemblyai",
"activity": "audio",
"endpointId": "v2/transcript",
"kind": "input",
"contentHash": "37c4c391443cb9c601f5cbe993422eb8207cfb155468decf184d0a5157e4f243",
"specRevision": null,
"provenance": {
"sourceUrl": "https://www.assemblyai.com/docs/openapi.json",
"sourceHash": "874d4c159d3adf6be986438d01502246300297a346fc7a7630753ff1e9ac38f3",
"fetchedAt": 1794460215,
"extractorVersion": "2",
"derivation": "upstream-spec",
"verifiedAt": null
},
"createdAt": 1794460215,
"supersededAt": null,
"schema": {
"x-label": "Transcript parameters",
"description": "The parameters for creating a transcript",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"allOf": [
{
"type": "object",
"required": [
"audio_url"
],
"properties": {
"audio_url": {
"x-label": "Audio URL",
"description": "The URL of the audio or video file to transcribe.",
"type": "string",
"format": "url"
}
},
"additionalProperties": false
},
{
"$ref": "#/$defs/TranscriptOptionalParams"
}
],
"example": {
"speech_model": null,
"language_detection": true,
"language_confidence_threshold": 0.7,
"audio_url": "https://assembly.ai/wildfires.mp3",
"punctuate": true,
"format_text": true,
"multichannel": true,
"webhook_url": "https://your-webhook-url/path",
"webhook_auth_header_name": "webhook-secret",
"webhook_auth_header_value": "webhook-secret-value",
"auto_highlights": true,
"audio_start_from": 10,
"audio_end_at": 280,
"filter_profanity": true,
"redact_pii": true,
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3",
"redact_pii_policies": [
"us_social_security_number",
"credit_card_number"
],
"redact_pii_sub": "hash",
"speaker_labels": true,
"speakers_expected": 2,
"content_safety": true,
"iab_categories": true,
"custom_spelling": [],
"disfluencies": false,
"sentiment_analysis": true,
"auto_chapters": false,
"entity_detection": true,
"speech_threshold": 0.5,
"summarization": false,
"summary_model": null,
"summary_type": null,
"custom_topics": true,
"topics": [],
"remove_audio_tags": null,
"domain": null,
"speech_understanding": {
"request": {
"translation": {
"target_languages": [
"es",
"de"
],
"formal": true,
"match_original_utterance": true
}
}
}
},
"$defs": {
"ActionItemsRequestBody": {
"type": "object",
"description": "Request body for [Action Items](https://www.assemblyai.com/docs/speech-understanding/action-items).",
"properties": {
"action_items": {
"type": "object",
"properties": {
"include_decisions": {
"type": "bool",
"description": "Option to include decision making in action items."
},
"effort": {
"type": "string",
"enum": [
"low",
"medium"
]
}
}
}
},
"required": [
"action_items"
]
},
"CustomFormattingRequestBody": {
"type": "object",
"description": "Request body for [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting).",
"properties": {
"custom_formatting": {
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "Date format pattern (e.g., `\"mm/dd/yyyy\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
},
"phone_number": {
"type": "string",
"description": "Phone number format pattern (e.g., `\"(xxx)xxx-xxxx\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
},
"email": {
"type": "string",
"description": "Email format pattern (e.g., `\"username@domain.com\"`). See [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) for more details."
}
}
}
},
"required": [
"custom_formatting"
]
},
"PiiPolicy": {
"x-label": "PII policy",
"description": "The type of PII to redact",
"x-fern-sdk-group-name": "transcripts",
"type": "string",
"enum": [
"account_number",
"banking_information",
"blood_type",
"credit_card_cvv",
"credit_card_expiration",
"credit_card_number",
"date",
"date_interval",
"date_of_birth",
"drivers_license",
"drug",
"duration",
"email_address",
"event",
"filename",
"gender",
"gender_sexuality",
"healthcare_number",
"injury",
"ip_address",
"language",
"location",
"location_address",
"location_address_street",
"location_city",
"location_coordinate",
"location_country",
"location_state",
"location_zip",
"marital_status",
"medical_condition",
"medical_process",
"money_amount",
"nationality",
"number_sequence",
"occupation",
"organization",
"organization_medical_facility",
"passport_number",
"password",
"person_age",
"person_name",
"phone_number",
"physical_attribute",
"political_affiliation",
"religion",
"sexuality",
"statistics",
"time",
"url",
"us_social_security_number",
"username",
"vehicle_id",
"zodiac_sign"
],
"x-fern-enum": {
"account_number": {
"description": "Customer account or membership identification number (e.g., Policy No. 10042992, Member ID: HZ-5235-001)"
},
"banking_information": {
"description": "Banking information, including account and routing numbers"
},
"blood_type": {
"description": "Blood type (e.g., O-, AB positive)"
},
"credit_card_cvv": {
"description": "Credit card verification code (e.g., CVV: 080)"
},
"credit_card_expiration": {
"description": "Expiration date of a credit card"
},
"credit_card_number": {
"description": "Credit card number"
},
"date": {
"description": "Specific calendar date (e.g., December 18)"
},
"date_interval": {
"description": "Broader time periods, including date ranges, months, seasons, years, and decades (e.g., 2020-2021, 5-9 May, January 1984)"
},
"date_of_birth": {
"description": "Date of birth (e.g., Date of Birth: March 7,1961)"
},
"drivers_license": {
"description": "Driver's license number. (e.g., DL# 356933-540)"
},
"drug": {
"description": "Medications, vitamins, or supplements (e.g., Advil, Acetaminophen, Panadol)"
},
"duration": {
"description": "Measurements of time expressed as a numerical value plus a unit (e.g., 8 months, 2 years)"
},
"email_address": {
"description": "Email address (e.g., support@assemblyai.com)"
},
"event": {
"description": "Name of an event or holiday (e.g., Olympics, Yom Kippur)"
},
"filename": {
"description": "Names of computer files, including the extension or filepath (e.g., Taxes/2012/brad-tax-returns.pdf)"
},
"gender": {
"description": "Terms indicating gender identity (e.g., female, male, non-binary)"
},
"gender_sexuality": {
"description": "Terms indicating gender identity or sexual orientation, including slang terms (e.g., female, bisexual, trans)"
},
"healthcare_number": {
"description": "Healthcare numbers and health plan beneficiary numbers (e.g., Policy No.: 5584-486-674-YM)"
},
"injury": {
"description": "Bodily injury (e.g., I broke my arm, I have a sprained wrist)"
},
"ip_address": {
"description": "Internet IP address, including IPv4 and IPv6 formats (e.g., 192.168.0.1)"
},
"language": {
"description": "Name of a natural language (e.g., Spanish, French)"
},
"location": {
"description": "Any Location reference including mailing address, postal code, city, state, province, country, or coordinates. (e.g., Lake Victoria, 145 Windsor St., 90210)"
},
"location_address": {
"description": "A complete mailing address (e.g., 145 Windsor St., Toronto, ON M5A 2P5)"
},
"location_address_street": {
"description": "Street-level component of an address (e.g., 145 Windsor St.)"
},
"location_city": {
"description": "City name (e.g., Toronto, San Francisco)"
},
"location_coordinate": {
"description": "Geographic coordinates (e.g., 40.7128° N, 74.0060° W)"
},
"location_country": {
"description": "Country name (e.g., Canada, United States)"
},
"location_state": {
"description": "State, province, or region name (e.g., Ontario, California)"
},
"location_zip": {
"description": "Postal or ZIP code (e.g., M5A 2P5, 90210)"
},
"marital_status": {
"description": "Terms indicating marital status (e.g., Single, common-law, ex-wife, married)"
},
"medical_condition": {
"description": "Name of a medical condition, disease, syndrome, deficit, or disorder (e.g., chronic fatigue syndrome, arrhythmia, depression)"
},
"medical_process": {
"description": "Medical process, including treatments, procedures, and tests (e.g., heart surgery, CT scan)"
},
"money_amount": {
"description": "Name and/or amount of currency (e.g., 15 pesos, $94.50)"
},
"nationality": {
"description": "Terms indicating nationality, ethnicity, or race (e.g., American, Asian, Caucasian)"
},
"number_sequence": {
"description": "Numerical PII (including alphanumeric strings) that doesn't fall under other categories"
},
"occupation": {
"description": "Job title or profession (e.g., professor, actors, engineer, CPA)"
},
"organization": {
"description": "Name of an organization (e.g., CNN, McDonalds, University of Alaska, Northwest General Hospital)"
},
"organization_medical_facility": {
"description": "Name of a medical facility (e.g., Mayo Clinic, Northwest General Hospital)"
},
"passport_number": {
"description": "Passport numbers, issued by any country (e.g., PA4568332, NU3C6L86S12)"
},
"password": {
"description": "Account passwords, PINs, access keys, or verification answers (e.g., 27%alfalfa, temp1234, My mother's maiden name is Smith)"
},
"person_age": {
"description": "Number associated with an age (e.g., 27, 75)"
},
"person_name": {
"description": "Name of a person (e.g., Bob, Doug Jones, Dr. Kay Martinez, MD)"
},
"phone_number": {
"description": "Telephone or fax number"
},
"physical_attribute": {
"description": "Distinctive bodily attributes, including race (e.g., I'm 190cm tall, He belongs to the Black students' association)"
},
"political_affiliation": {
"description": "Terms referring to a political party, movement, or ideology (e.g., Republican, Liberal)"
},
"religion": {
"description": "Terms indicating religious affiliation (e.g., Hindu, Catholic)"
},
"sexuality": {
"description": "Terms indicating sexual orientation (e.g., heterosexual, bisexual, gay)"
},
"statistics": {
"description": "Medical statistics (e.g., 18%, 18 percent)"
},
"time": {
"description": "Expressions indicating clock times (e.g., 19:37:28, 10pm EST)"
},
"url": {
"description": "Internet addresses (e.g., https://www.assemblyai.com/)"
},
"us_social_security_number": {
"description": "Social Security Number or equivalent"
},
"username": {
"description": "Usernames, login names, or handles (e.g., @AssemblyAI)"
},
"vehicle_id": {
"description": "Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers (e.g., 5FNRL38918B111818, BIF7547)"
},
"zodiac_sign": {
"description": "Names of Zodiac signs (e.g., Aries, Taurus)"
}
},
"x-aai-enum": {
"account_number": {
"label": "Account number"
},
"banking_information": {
"label": "Banking information"
},
"blood_type": {
"label": "Blood type"
},
"credit_card_cvv": {
"label": "Credit card CVV"
},
"credit_card_expiration": {
"label": "Credit card expiration"
},
"credit_card_number": {
"label": "Credit card number"
},
"date": {
"label": "Date"
},
"date_interval": {
"label": "Date interval"
},
"date_of_birth": {
"label": "Date of birth"
},
"drivers_license": {
"label": "Driver's license"
},
"drug": {
"label": "Drug"
},
"duration": {
"label": "Duration"
},
"email_address": {
"label": "Email address"
},
"event": {
"label": "Event"
},
"filename": {
"label": "Filename"
},
"gender": {
"label": "Gender"
},
"gender_sexuality": {
"label": "Gender sexuality"
},
"healthcare_number": {
"label": "Healthcare number"
},
"injury": {
"label": "Injury"
},
"ip_address": {
"label": "IP address"
},
"language": {
"label": "Language"
},
"location": {
"label": "Location"
},
"location_address": {
"label": "Location address"
},
"location_address_street": {
"label": "Location address street"
},
"location_city": {
"label": "Location city"
},
"location_coordinate": {
"label": "Location coordinate"
},
"location_country": {
"label": "Location country"
},
"location_state": {
"label": "Location state"
},
"location_zip": {
"label": "Location ZIP"
},
"marital_status": {
"label": "Marital status"
},
"medical_condition": {
"label": "Medical condition"
},
"medical_process": {
"label": "Medical process"
},
"money_amount": {
"label": "Money amount"
},
"nationality": {
"label": "Nationality"
},
"number_sequence": {
"label": "Number sequence"
},
"occupation": {
"label": "Occupation"
},
"organization": {
"label": "Organization"
},
"organization_medical_facility": {
"label": "Organization medical facility"
},
"passport_number": {
"label": "Passport number"
},
"password": {
"label": "Password"
},
"person_age": {
"label": "Person age"
},
"person_name": {
"label": "Person name"
},
"phone_number": {
"label": "Phone number"
},
"physical_attribute": {
"label": "Physical attribute"
},
"political_affiliation": {
"label": "Political affiliation"
},
"religion": {
"label": "Religion"
},
"sexuality": {
"label": "Sexuality"
},
"statistics": {
"label": "Statistics"
},
"time": {
"label": "Time"
},
"url": {
"label": "URL"
},
"us_social_security_number": {
"label": "US Social Security Number"
},
"username": {
"label": "Username"
},
"vehicle_id": {
"label": "Vehicle ID"
},
"zodiac_sign": {
"label": "Zodiac sign"
}
}
},
"RedactPiiAudioQuality": {
"x-label": "Redact PII audio quality",
"type": "string",
"description": "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/pii-redaction#request-for-redacted-audio) for more details.",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"mp3",
"wav"
],
"x-fern-enum": {
"mp3": {
"description": "MP3 audio format is lower quality and lower size than WAV.",
"casing": {
"camel": "mp3",
"snake": "mp3",
"pascal": "Mp3",
"screamingSnake": "MP3"
}
},
"wav": {
"description": "WAV audio format is the highest quality (no compression) and larger size than MP3."
}
},
"x-aai-enum": {
"mp3": {
"label": "MP3"
},
"wav": {
"label": "WAV"
}
},
"example": "mp3"
},
"SpeakerIdentificationRequestBody": {
"type": "object",
"description": "Request body for [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification).",
"properties": {
"speaker_identification": {
"type": "object",
"properties": {
"speaker_type": {
"type": "string",
"enum": [
"role",
"name"
],
"description": "Type of speaker identification. See [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) for details on each type."
},
"known_values": {
"type": "array",
"items": {
"type": "string"
},
"description": "Required if speaker_type is \"role\". Each value must be 35 characters or less."
},
"speakers": {
"type": "array",
"description": "An array of speaker objects with metadata to improve identification accuracy. Each object should include a `role` or `name` (depending on `speaker_type`) and an optional `description` to help the model identify the speaker. You can also include any additional custom properties (e.g., `company`, `title`) to provide more context. Use this as an alternative to `known_values` when you want to provide additional context about each speaker.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "The role of the speaker. Required when `speaker_type` is \"role\"."
},
"name": {
"type": "string",
"description": "The name of the speaker. Required when `speaker_type` is \"name\"."
},
"description": {
"type": "string",
"description": "A description of the speaker to help the model identify them based on conversational context."
}
},
"additionalProperties": true
}
}
},
"required": [
"speaker_type"
]
}
},
"required": [
"speaker_identification"
]
},
"SpeechModel": {
"x-label": "Speech model",
"type": "string",
"description": "The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models.",
"enum": [
"universal-3-5-pro",
"universal-2"
],
"x-fern-sdk-group-name": "transcripts"
},
"SubstitutionPolicy": {
"x-label": "Redact PII substitution",
"type": "string",
"x-fern-sdk-group-name": "transcripts",
"description": "The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"enum": [
"entity_name",
"hash"
],
"x-aai-enum": {
"entity_name": {
"label": "Entity name"
},
"hash": {
"label": "Hash"
}
}
},
"SummarizationRequestBody": {
"type": "object",
"description": "Request body for [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization).",
"properties": {
"summariazation": {
"type": "object",
"properties": {
"summary_type": {
"type": "string",
"enum": [
"paragraph",
"bullets"
],
"description": "Type of summary. Bullets returns short bullet point style summaries, paragraph is generally more verbose and detailed."
},
"effort": {
"type": "string",
"enum": [
"low",
"medium"
]
}
}
}
},
"required": [
"summarization"
]
},
"SummaryModel": {
"type": "string",
"x-label": "Summary model",
"description": "The model to summarize the transcript",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"informative",
"conversational",
"catchy"
],
"x-aai-enum": {
"informative": {
"label": "Informative"
},
"conversational": {
"label": "Conversational"
},
"catchy": {
"label": "Catchy"
}
}
},
"SummaryType": {
"type": "string",
"x-label": "Summary type",
"description": "The type of summary",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"bullets",
"bullets_verbose",
"gist",
"headline",
"paragraph"
],
"x-aai-enum": {
"bullets": {
"label": "Bullets"
},
"bullets_verbose": {
"label": "Bullets verbose"
},
"gist": {
"label": "Gist"
},
"headline": {
"label": "Headline"
},
"paragraph": {
"label": "Paragraph"
}
}
},
"TranscriptCustomSpelling": {
"x-label": "Custom spelling",
"description": "Object containing words or phrases to replace, and the word or phrase to replace with",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"from": {
"x-label": "From",
"description": "Words or phrases to replace",
"type": "array",
"items": {
"x-label": "Word or phrase",
"description": "Word or phrase to replace",
"type": "string"
}
},
"to": {
"x-label": "To",
"description": "Word to replace with",
"type": "string"
}
},
"required": [
"from",
"to"
],
"example": {
"from": [
"dicarlo"
],
"to": "Decarlo"
}
},
"TranscriptLanguageCode": {
"x-label": "Language code",
"type": "string",
"description": "The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\n",
"x-fern-sdk-group-name": "transcripts",
"enum": [
"en",
"en_au",
"en_uk",
"en_us",
"es",
"fr",
"de",
"it",
"pt",
"nl",
"af",
"sq",
"am",
"ar",
"hy",
"as",
"az",
"ba",
"eu",
"be",
"bn",
"bs",
"br",
"bg",
"my",
"ca",
"zh",
"hr",
"cs",
"da",
"et",
"fo",
"fi",
"gl",
"ka",
"el",
"gu",
"ht",
"ha",
"haw",
"he",
"hi",
"hu",
"is",
"id",
"ja",
"jw",
"kn",
"kk",
"km",
"ko",
"lo",
"la",
"lv",
"ln",
"lt",
"lb",
"mk",
"mg",
"ms",
"ml",
"mt",
"mi",
"mr",
"mn",
"ne",
"no",
"nn",
"oc",
"pa",
"ps",
"fa",
"pl",
"ro",
"ru",
"sa",
"sr",
"sn",
"sd",
"si",
"sk",
"sl",
"so",
"su",
"sw",
"sv",
"tl",
"tg",
"ta",
"tt",
"te",
"th",
"bo",
"tr",
"tk",
"uk",
"ur",
"uz",
"vi",
"cy",
"yi",
"yo"
],
"x-aai-enum": {
"en": {
"label": "English (global)"
},
"en_au": {
"label": "English (Australian)"
},
"en_uk": {
"label": "English (British)"
},
"en_us": {
"label": "English (US)"
},
"es": {
"label": "Spanish"
},
"fr": {
"label": "French"
},
"de": {
"label": "German"
},
"it": {
"label": "Italian"
},
"pt": {
"label": "Portuguese"
},
"nl": {
"label": "Dutch"
},
"af": {
"label": "Afrikaans"
},
"sq": {
"label": "Albanian"
},
"am": {
"label": "Amharic"
},
"ar": {
"label": "Arabic"
},
"hy": {
"label": "Armenian"
},
"as": {
"label": "Assamese"
},
"az": {
"label": "Azerbaijani"
},
"ba": {
"label": "Bashkir"
},
"eu": {
"label": "Basque"
},
"be": {
"label": "Belarusian"
},
"bn": {
"label": "Bengali"
},
"bs": {
"label": "Bosnian"
},
"br": {
"label": "Breton"
},
"bg": {
"label": "Bulgarian"
},
"my": {
"label": "Burmese"
},
"ca": {
"label": "Catalan"
},
"zh": {
"label": "Chinese"
},
"hr": {
"label": "Croatian"
},
"cs": {
"label": "Czech"
},
"da": {
"label": "Danish"
},
"et": {
"label": "Estonian"
},
"fo": {
"label": "Faroese"
},
"fi": {
"label": "Finnish"
},
"gl": {
"label": "Galician"
},
"ka": {
"label": "Georgian"
},
"el": {
"label": "Greek"
},
"gu": {
"label": "Gujarati"
},
"ht": {
"label": "Haitian"
},
"ha": {
"label": "Hausa"
},
"haw": {
"label": "Hawaiian"
},
"he": {
"label": "Hebrew"
},
"hi": {
"label": "Hindi"
},
"hu": {
"label": "Hungarian"
},
"is": {
"label": "Icelandic"
},
"id": {
"label": "Indonesian"
},
"ja": {
"label": "Japanese"
},
"jw": {
"label": "Javanese"
},
"kn": {
"label": "Kannada"
},
"kk": {
"label": "Kazakh"
},
"km": {
"label": "Khmer"
},
"ko": {
"label": "Korean"
},
"lo": {
"label": "Lao"
},
"la": {
"label": "Latin"
},
"lv": {
"label": "Latvian"
},
"ln": {
"label": "Lingala"
},
"lt": {
"label": "Lithuanian"
},
"lb": {
"label": "Luxembourgish"
},
"mk": {
"label": "Macedonian"
},
"mg": {
"label": "Malagasy"
},
"ms": {
"label": "Malay"
},
"ml": {
"label": "Malayalam"
},
"mt": {
"label": "Maltese"
},
"mi": {
"label": "Maori"
},
"mr": {
"label": "Marathi"
},
"mn": {
"label": "Mongolian"
},
"ne": {
"label": "Nepali"
},
"no": {
"label": "Norwegian"
},
"nn": {
"label": "Norwegian Nynorsk"
},
"oc": {
"label": "Occitan"
},
"pa": {
"label": "Panjabi"
},
"ps": {
"label": "Pashto"
},
"fa": {
"label": "Persian"
},
"pl": {
"label": "Polish"
},
"ro": {
"label": "Romanian"
},
"ru": {
"label": "Russian"
},
"sa": {
"label": "Sanskrit"
},
"sr": {
"label": "Serbian"
},
"sn": {
"label": "Shona"
},
"sd": {
"label": "Sindhi"
},
"si": {
"label": "Sinhala"
},
"sk": {
"label": "Slovak"
},
"sl": {
"label": "Slovenian"
},
"so": {
"label": "Somali"
},
"su": {
"label": "Sundanese"
},
"sw": {
"label": "Swahili"
},
"sv": {
"label": "Swedish"
},
"tl": {
"label": "Tagalog"
},
"tg": {
"label": "Tajik"
},
"ta": {
"label": "Tamil"
},
"tt": {
"label": "Tatar"
},
"te": {
"label": "Telugu"
},
"th": {
"label": "Thai"
},
"bo": {
"label": "Tibetan"
},
"tr": {
"label": "Turkish"
},
"tk": {
"label": "Turkmen"
},
"uk": {
"label": "Ukrainian"
},
"ur": {
"label": "Urdu"
},
"uz": {
"label": "Uzbek"
},
"vi": {
"label": "Vietnamese"
},
"cy": {
"label": "Welsh"
},
"yi": {
"label": "Yiddish"
},
"yo": {
"label": "Yoruba"
}
}
},
"TranscriptOptionalParams": {
"x-label": "Optional transcript parameters",
"description": "The parameters for creating a transcript",
"x-fern-sdk-group-name": "transcripts",
"type": "object",
"additionalProperties": false,
"properties": {
"audio_end_at": {
"x-label": "Audio end at",
"description": "The point in time, in milliseconds, to stop transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": "integer"
},
"audio_start_from": {
"x-label": "Audio start from",
"description": "The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.",
"type": "integer"
},
"auto_chapters": {
"x-label": "Auto chapters",
"description": "Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters), can be true or false. Requires `punctuate` to be `true`, and cannot be enabled together with `summarization`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": "boolean",
"default": false,
"deprecated": true
},
"auto_highlights": {
"x-label": "Key phrases",
"description": "Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases), either true or false",
"type": "boolean",
"default": false
},
"content_safety": {
"x-label": "Content Moderation",
"description": "Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false",
"type": "boolean",
"default": false
},
"content_safety_confidence": {
"x-label": "Content Moderation confidence",
"description": "The confidence threshold for the [Content Moderation](https://www.assemblyai.com/docs/content-moderation) model. Values must be between 25 and 100. Requires `content_safety` to be enabled; otherwise it's ignored.",
"type": "integer",
"default": 50,
"minimum": 25,
"maximum": 100
},
"custom_spelling": {
"x-label": "Custom spellings",
"description": "Customize how words are spelled and formatted using to and from values. Each `to` value must be a single word, and each `from` phrase can contain at most 5 words. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details.",
"type": "array",
"items": {
"x-label": "Custom spelling",
"$ref": "#/$defs/TranscriptCustomSpelling"
}
},
"disfluencies": {
"x-label": "Disfluencies",
"description": "Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like \"umm\", in your media file; can be true or false. Supported on Universal-3.6 Pro Preview, Universal-3.5 Pro and Universal-2. Defaults to true when the first `speech_models` entry is `universal-3-6-pro-preview`, and to false otherwise.",
"type": "boolean"
},
"domain": {
"x-label": "Domain",
"description": "Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `\"medical-v1\"` to enable [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) for improved accuracy of medication names, both generic and brand-name. Set to `\"veterinary-v1\"` to enable [Veterinary Mode](https://www.assemblyai.com/docs/pre-recorded-audio/veterinary-mode) (beta) for improved accuracy of veterinary terminology.\n\nMedical Mode supported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If `medical-v1` is used with an unsupported language, the parameter is ignored and a warning is returned.\n",
"type": [
"string",
"null"
],
"enum": [
"medical-v1",
"veterinary-v1",
null
],
"default": null
},
"entity_detection": {
"x-label": "Entity Detection",
"description": "Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection), can be true or false",
"type": "boolean",
"default": false
},
"filter_profanity": {
"x-label": "Filter profanity",
"description": "Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details.",
"type": "boolean",
"default": false
},
"format_text": {
"x-label": "Format text",
"description": "Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false",
"type": "boolean",
"default": true
},
"iab_categories": {
"x-label": "Topic Detection",
"description": "Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection), can be true or false",
"type": "boolean",
"default": false
},
"keyterms_prompt": {
"x-label": "Keyterms prompt",
"description": "Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3.5 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting#keyterms-prompting) for more details.\n",
"type": "array",
"items": {
"x-label": "Keyterm",
"type": "string"
}
},
"language_code": {
"x-label": "Language code",
"description": "The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages).\nIf you don't specify a language, it's detected automatically. Cannot be used together with `language_detection`.\n",
"oneOf": [
{
"anyOf": [
{
"$ref": "#/$defs/TranscriptLanguageCode"
},
{
"type": "string"
}
]
},
{
"type": "null"
}
],
"x-ts-type": "LiteralUnion<TranscriptLanguageCode, string> | null",
"x-go-type": "TranscriptLanguageCode"
},
"language_codes": {
"description": "The language codes of your audio file. Used for [Code switching](/speech-to-text/pre-recorded-audio/code-switching)\nOne of the values specified must be `en`.\n",
"type": [
"array",
"null"
],
"items": {
"x-label": "Language code",
"$ref": "#/$defs/TranscriptLanguageCode"
}
},
"language_confidence_threshold": {
"x-label": "Language confidence threshold",
"description": "The confidence threshold for the automatically detected language.\nAn error will be returned if the language confidence is below this threshold.\nDefaults to 0. Can only be set when `language_detection` is enabled. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "number",
"format": "float",
"minimum": 0,
"maximum": 1,
"default": 0
},
"language_detection": {
"x-label": "Language detection",
"description": "[Automatic language detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) identifies the spoken language and routes the request to the best model. It's applied automatically when you don't specify a `language_code`. Set to `false` only together with a `language_code`; disabling it without specifying a language returns an error.",
"type": "boolean"
},
"language_detection_options": {
"x-label": "Specify options for Automatic Language Detection.",
"description": "Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection).",
"type": "object",
"additionalProperties": false,
"properties": {
"expected_languages": {
"x-label": "Expected languages",
"description": "List of languages expected in the audio file. Defaults to `[\"all\"]` when unspecified. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.",
"type": "array",
"items": {
"x-label": "language",
"type": "string"
}
},
"fallback_language": {
"x-label": "Fallback language",
"description": "If the detected language of the audio file is not in the list of expected languages, the `fallback_language` is used. Specify `[\"auto\"]` to let our model choose the fallback language from `expected_languages` with the highest confidence score. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"default": "auto"
},
"code_switching": {
"x-label": "Code switching",
"description": "Whether [code switching](/speech-to-text/pre-recorded-audio/code-switching) should be detected.\n",
"type": "boolean",
"default": false
},
"code_switching_confidence_threshold": {
"x-label": "Code switching confidence threshold",
"description": "The confidence threshold for [code switching](/speech-to-text/pre-recorded-audio/code-switching) detection. If the code switching confidence is below this threshold, the transcript will be processed in the language with the highest `language_detection_confidence` score.\n",
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.3
},
"localization": {
"x-label": "Localization",
"description": "Render the transcript in a regional variant of the detected language. Supported values are `en_au` (Australian English) and `en_uk` (British English) — only English is supported today, and you can specify at most one locale per base language. Base or default-region codes such as `en` and `en_us` are not localization variants and return a `400`.\n\nWhen the detected language matches the requested locale's base language, the transcript uses that locale's spelling and `language_code` returns the region-aware code (for example `en_au`) instead of the base `en`. Otherwise, when the detected language isn't available as a locale, the option is ignored. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "array",
"items": {
"x-label": "locale",
"type": "string"
}
},
"on_no_speech_detected": {
"x-label": "On no speech detected",
"description": "Controls what happens when no speech is detected in the audio. With `error` (the default), the transcript fails and the reason is returned in `error`. With `fallback`, the transcript completes with an empty `text`, `language_code` is set to the `fallback_language`, and an explanatory warning is returned in `metadata.warnings`.\n\n`fallback` requires `fallback_language` to be set to a specific language code; `auto` returns a `400`. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.\n",
"type": "string",
"enum": [
"error",
"fallback"
],
"default": "error"
}
}
},
"multichannel": {
"x-label": "Multichannel",
"description": "Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false.",
"type": "boolean",
"default": false
},
"prompt": {
"x-label": "Prompt",
"description": "Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"type": "string"
},
"punctuate": {
"x-label": "Punctuate",
"description": "Enable [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false",
"type": "boolean",
"default": true
},
"redact_pii": {
"x-label": "Redact PII",
"description": "Redact PII from the transcribed text using the Redact PII model, can be true or false. Requires `format_text` to be `true`. See [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"type": "boolean",
"default": false
},
"redact_pii_audio": {
"x-label": "Redact PII audio",
"description": "Generate a copy of the original media file with spoken PII \"beeped\" out, can be true or false. Requires `redact_pii` to be `true`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.",
"type": "boolean",
"default": false
},
"redact_pii_audio_options": {
"x-label": "Specify options for PII redacted audio files.",
"description": "Specify options for [PII redacted audio](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) files.",
"type": "object",
"additionalProperties": false,
"properties": {
"return_redacted_no_speech_audio": {
"x-label": "Return redacted no speech audio",
"description": "By default, audio redaction provides redacted audio URLs only when speech is detected. However, if your use-case specifically requires redacted audio files even for silent audio files without any dialogue, you can opt to receive these URLs by setting this parameter to `true`. Requires `redact_pii_audio` to be `true`.",
"type": "boolean",
"default": false
},
"override_audio_redaction_method": {
"x-label": "Override audio redaction method",
"description": "Specify the method used to redact audio. By default, redacted audio uses a beep sound. Set to `silence` to replace PII with silence instead of a beep.",
"type": "string",
"enum": [
"silence"
]
}
}
},
"redact_pii_audio_quality": {
"x-label": "Redact PII audio quality",
"description": "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/pii-redaction#request-for-redacted-audio) for more details.",
"default": "mp3",
"$ref": "#/$defs/RedactPiiAudioQuality"
},
"redact_pii_policies": {
"x-label": "Redact PII policies",
"description": "The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"type": "array",
"items": {
"x-label": "PII policy",
"$ref": "#/$defs/PiiPolicy"
}
},
"redact_pii_sub": {
"x-label": "Redact PII substitution",
"description": "The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.",
"oneOf": [
{
"$ref": "#/$defs/SubstitutionPolicy"
},
{
"type": "null"
}
],
"default": "hash"
},
"redact_pii_return_unredacted": {
"x-label": "Return unredacted transcript",
"description": "When set to `true`, returns the original unredacted transcript alongside the redacted one in the same response. Requires `redact_pii` to be `true`, otherwise a 400 error is returned.\n\nWhen enabled, the response includes the additional fields `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. The existing `text`, `words`, and `utterances` fields remain fully redacted. When disabled (default), the response is unchanged and contains only the redacted transcript. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.\n",
"type": "boolean",
"default": false
},
"redact_static_entities": {
"x-label": "Redact static entities",
"description": "A map of user-defined terms to redact, where each key is a redaction label and each value is a list of exact terms to match (e.g. `{ \"INTERNAL_TOOL\": [\"Bearclaw\", \"Cubclaw\"] }`). Each matching term in the transcript is redacted using the `redact_pii_sub` substitution, on top of standard PII Redaction. Useful for redacting specific, predefined terms (proprietary names, internal codenames) that aren't general PII categories.\n\nThis is a literal find-and-replace (tolerant of casing, surrounding punctuation, and minor spacing/hyphenation), not a model — it does not generalize beyond the terms you provide. Requires `redact_pii` to be `true`, otherwise a 400 error is returned. When `redact_pii_audio` is enabled, matched terms are also redacted in the audio output. You can provide up to 100 labels, each with up to 200 terms of at most 200 characters; a label may contain only letters, numbers, spaces, underscores, and hyphens (max 80 characters). See [Static Entity Redaction](https://www.assemblyai.com/docs/guardrails/redact-pii-from-transcripts#static-entity-redaction) for more details.\n",
"type": "object",
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"sentiment_analysis": {
"x-label": "Sentiment Analysis",
"description": "Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis), can be true or false. Requires `punctuate` to be `true`.",
"type": "boolean",
"default": false
},
"speaker_labels": {
"x-label": "Speaker labels",
"description": "Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false. Requires `punctuate` to be `true`.",
"type": "boolean",
"default": false
},
"speaker_options": {
"x-label": "Specify options for speaker diarization.",
"description": "Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers). Use this to set a range of possible speakers. Requires `speaker_labels` to be `true`, and cannot be used together with `speakers_expected`. When both bounds are set, `min_speakers_expected` must be less than or equal to `max_speakers_expected`.",
"type": "object",
"additionalProperties": false,
"properties": {
"min_speakers_expected": {
"x-label": "Minimum speakers expected",
"description": "A hard lower limit on the number of speaker labels — the model won't return fewer speakers than this. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.",
"type": "integer"
},
"max_speakers_expected": {
"x-label": "Maximum speakers expected",
"description": "<Warning>Setting this parameter too high may hurt model accuracy</Warning>\nA hard upper limit on the number of speaker labels. If more people speak than this value, the additional speakers are merged into existing labels. Setting it higher than the true number of speakers can cause the model to over-split and return more speakers than are actually present. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.\n",
"type": "integer"
},
"include_speaker_confidence": {
"x-label": "Include speaker confidence",
"description": "When `true`, includes a `speaker_confidence` field per word and per utterance in the response. See [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#configuration) for more details.",
"type": "boolean",
"default": false
}
}
},
"speakers_expected": {
"x-label": "Speakers expected",
"description": "Tells the speaker label model how many speakers it should attempt to identify. Requires `speaker_labels` to be `true` and must be a positive integer; cannot be used together with `speaker_options`. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details.",
"type": [
"integer",
"null"
],
"default": null
},
"speech_models": {
"x-label": "Speech models",
"description": "Optional. List one or more speech models in priority order. Supported values: `universal-3-5-pro`, `universal-2`. If omitted, defaults to `[\"universal-3-5-pro\", \"universal-2\"]`. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.\n",
"type": "array",
"items": {
"x-label": "Speech model",
"$ref": "#/$defs/SpeechModel"
},
"default": [
"universal-3-5-pro",
"universal-2"
]
},
"speech_threshold": {
"x-label": "Speech threshold",
"description": "Reject audio files that contain less than this fraction of speech.\nValid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.\n",
"type": [
"number",
"null"
],
"format": "float",
"minimum": 0,
"maximum": 1,
"default": 0
},
"speech_understanding": {
"x-label": "Speech Understanding",
"description": "Enable speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n",
"type": "object",
"properties": {
"request": {
"oneOf": [
{
"$ref": "#/$defs/TranslationRequestBody"
},
{
"$ref": "#/$defs/SpeakerIdentificationRequestBody"
},
{
"$ref": "#/$defs/CustomFormattingRequestBody"
},
{
"$ref": "#/$defs/SummarizationRequestBody"
},
{
"$ref": "#/$defs/ActionItemsRequestBody"
}
]
}
},
"required": [
"request"
]
},
"summarization": {
"x-label": "Enable Summarization",
"description": "Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization), can be true or false. Requires both `punctuate` and `format_text` to be `true`, and cannot be enabled together with `auto_chapters`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n",
"type": "boolean",
"default": false,
"deprecated": true
},
"summary_model": {
"x-label": "Summary model",
"description": "The model to summarize the transcript. Must be set together with `summary_type`. Compatibility - `catchy` supports `gist` and `headline`; `informative` and `conversational` support `headline`, `paragraph`, `bullets`, and `bullets_verbose`. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"default": "informative",
"deprecated": true,
"$ref": "#/$defs/SummaryModel"
},
"summary_type": {
"x-label": "Summary type",
"description": "The type of summary. Must be set together with `summary_model`; see `summary_model` for the supported model and type combinations. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details.",
"default": "bullets",
"deprecated": true,
"$ref": "#/$defs/SummaryType"
},
"remove_audio_tags": {
"x-label": "Remove audio tags",
"description": "Universal-3.5 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. By default, all inline annotations are removed.\n\nNote: This parameter is only supported for the Universal-3.5 Pro model.\n",
"oneOf": [
{
"type": "string",
"enum": [
"all",
"speaker"
]
},
{
"type": "null"
}
],
"default": "all"
},
"temperature": {
"x-label": "Temperature",
"description": "Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter only takes effect on the Universal-3.5 Pro model.\n",
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0
},
"webhook_auth_header_name": {
"x-label": "Webhook auth header name",
"description": "The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests. Must be 1-1000 characters and contain only ASCII letters, numbers, hyphens, and underscores. Requires `webhook_auth_header_value` and `webhook_url` to also be set.",
"type": [
"string",
"null"
],
"default": null
},
"webhook_auth_header_value": {
"x-label": "Webhook auth header value",
"description": "The header value to send back with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests for added security. Must be 1-1000 characters and must not contain carriage returns or newlines. Requires `webhook_auth_header_name` and `webhook_url` to also be set.",
"type": [
"string",
"null"
],
"default": null
},
"webhook_url": {
"x-label": "Webhook URL",
"description": "The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.\n",
"type": "string",
"format": "url"
},
"custom_topics": {
"x-label": "Enable custom topics",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "boolean",
"default": false,
"deprecated": true
},
"speech_model": {
"x-label": "Speech model",
"description": "This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).\n",
"oneOf": [
{
"$ref": "#/$defs/SpeechModel"
},
{
"type": "null"
}
],
"deprecated": true
},
"topics": {
"x-label": "Custom topics",
"description": "This parameter does not currently have any functionality attached to it.",
"type": "array",
"items": {
"x-label": "Topic",
"type": "string"
},
"deprecated": true
}
},
"example": {
"speech_model": null,
"language_detection": true,
"language_confidence_threshold": 0.7,
"punctuate": true,
"format_text": true,
"multichannel": true,
"webhook_url": "https://your-webhook-url.tld/path",
"webhook_auth_header_name": "webhook-secret",
"webhook_auth_header_value": "webhook-secret-value",
"auto_highlights": true,
"audio_start_from": 10,
"audio_end_at": 280,
"filter_profanity": true,
"redact_pii": true,
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3",
"redact_pii_policies": [
"us_social_security_number",
"credit_card_number"
],
"redact_pii_sub": "hash",
"speaker_labels": true,
"speakers_expected": 2,
"content_safety": true,
"iab_categories": true,
"custom_spelling": [],
"disfluencies": false,
"sentiment_analysis": true,
"auto_chapters": false,
"entity_detection": true,
"speech_threshold": 0.5,
"summarization": false,
"summary_model": null,
"summary_type": null,
"custom_topics": true,
"topics": [],
"remove_audio_tags": null,
"domain": null,
"speech_understanding": {
"request": {
"translation": {
"target_languages": [
"es",
"de"
],
"formal": true,
"match_original_utterance": true
}
}
}
}
},
"TranslationRequestBody": {
"x-label": "Translation request body",
"description": "Request body for [Translation](https://www.assemblyai.com/docs/speech-understanding/translation).",
"type": "object",
"properties": {
"translation": {
"type": "object",
"properties": {
"target_languages": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of target language codes (e.g., `[\"es\", \"de\"]`). See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for supported languages."
},
"formal": {
"type": "boolean",
"description": "Use formal language style. See [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) for more details.",
"default": true
},
"match_original_utterance": {
"type": "boolean",
"description": "When enabled with Speaker Labels, returns translated text in the utterances array. Each utterance will include a `translated_texts` key containing translations for each target language.",
"default": false
}
},
"required": [
"target_languages"
]
}
},
"required": [
"translation"
]
}
}
}
}Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"assemblyai","endpointId":"v2/transcript","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}