From 4899980deaa272583bcb62575fe71a3f02cb0e58 Mon Sep 17 00:00:00 2001 From: AssemblyAI Date: Fri, 10 Nov 2023 20:26:19 -0500 Subject: [PATCH] Project import generated by Copybara. GitOrigin-RevId: 25cdd75a3767a82db6ec4a894000472e9cb4b763 --- asyncapi.yml | 46 ++-- openapi.yml | 576 +++++++++++++++++++++++++++++---------------------- 2 files changed, 350 insertions(+), 272 deletions(-) diff --git a/asyncapi.yml b/asyncapi.yml index 41703a6..e216a2a 100644 --- a/asyncapi.yml +++ b/asyncapi.yml @@ -36,18 +36,18 @@ channels: type: object properties: Authentication: - description: Authenticate using your AssemblyAI API key. + description: Authenticate using your AssemblyAI API key type: string query: type: object properties: sample_rate: - description: The sample rate of the streamed audio. + description: The sample rate of the streamed audio type: integer word_boost: description: | Add up to 2500 characters of custom vocabulary. - The parameter should map to a JSON encoded list of strings. + The parameter value must be a JSON encoded array of strings. type: string token: description: "Authenticate using a [generated temporary token](https://www.assemblyai.com/docs/Guides/real-time_streaming_transcription#creating-temporary-authentication-tokens)" @@ -100,7 +100,7 @@ components: $ref: "#/components/schemas/RealtimeError" PartialTranscript: messageId: partialTranscript - summary: As you send audio data to the API, the API immediately starts responding with Partial Results. + summary: As you send audio data to the API, the API immediately starts responding with Partial Transcript results. payload: $ref: "#/components/schemas/PartialTranscript" FinalTranscript: @@ -117,7 +117,7 @@ components: - message_type properties: message_type: - description: Describes the type of the message. + description: Describes the type of the message $ref: "#/components/schemas/MessageType" RealtimeMessage: oneOf: @@ -155,14 +155,14 @@ components: - expires_at properties: message_type: - description: Describes the type of the message. + description: Describes the type of the message type: string const: SessionBegins session_id: - description: Unique identifier for the established session. + description: Unique identifier for the established session type: string expires_at: - description: Timestamp when this session will expire. + description: Timestamp when this session will expire type: string pattern: '^(?:(\d{4}-\d{2}-\d{2})T(\d{2}:\d{2}:\d{2}(?:\.\d+)?))$' x-fern-type: datetime @@ -175,7 +175,7 @@ components: - message_type properties: message_type: - description: Describes the type of the message. + description: Describes the type of the message type: string const: SessionTerminated additionalProperties: false @@ -190,27 +190,29 @@ components: - created properties: audio_start: - description: Start time of audio sample relative to session start, in milliseconds. + description: Start time of audio sample relative to session start, in milliseconds type: integer audio_end: - description: End time of audio sample relative to session start, in milliseconds. + description: End time of audio sample relative to session start, in milliseconds type: integer confidence: - description: The confidence score of the entire transcription, between 0 and 1. + description: The confidence score of the entire transcription, between 0 and 1 type: number minimum: 0 maximum: 1 format: double text: - description: The partial transcript for your audio. + description: The partial transcript for your audio type: string words: - description: An array of objects, with the information for each word in the transcription text. Includes the start/end time (in milliseconds) of the word, the confidence score of the word, and the text (i.e. the word itself). + description: | + An array of objects, with the information for each word in the transcription text. + Includes the start and end time of the word in milliseconds, the confidence score of the word, and the text, which is the word itself. type: array items: $ref: "#/components/schemas/Word" created: - description: The timestamp for the partial transcript. + description: The timestamp for the partial transcript type: string pattern: '^(?:(\d{4}-\d{2}-\d{2})T(\d{2}:\d{2}:\d{2}(?:\.\d+)?))$' x-fern-type: datetime @@ -223,7 +225,7 @@ components: - message_type properties: message_type: - description: Describes the type of message. + description: Describes the type of message type: string const: PartialTranscript additionalProperties: false @@ -237,14 +239,14 @@ components: - text_formatted properties: message_type: - description: Describes the type of message. + description: Describes the type of message type: string const: FinalTranscript punctuated: - description: Whether the text has been punctuated and cased. + description: Whether the text is punctuated and cased type: boolean text_formatted: - description: Whether the text has been formatted (e.g. Dollar -> $) + description: Whether the text is formatted, for example Dollar -> $ type: boolean additionalProperties: false Word: @@ -277,7 +279,7 @@ components: - audio_data properties: audio_data: - description: Raw audio data, base64 encoded. This can be the raw data recorded directly from a microphone or read from an audio file. + description: Base64 encoded raw audio data type: string additionalProperties: false TerminateSession: @@ -288,12 +290,12 @@ components: - terminate_session properties: terminate_session: - description: A boolean value to communicate that you wish to end your real-time session forever. + description: Set to true to end your real-time session forever type: boolean additionalProperties: false securitySchemes: ApiKey: - description: Authenticate using your AssemblyAI API key. + description: Authenticate using your AssemblyAI API key type: httpApiKey in: header name: Authorization diff --git a/openapi.yml b/openapi.yml index 845de0f..57d515a 100644 --- a/openapi.yml +++ b/openapi.yml @@ -25,6 +25,7 @@ tags: description: Real-time transcription externalDocs: url: https://www.assemblyai.com/docs/Guides/real-time_streaming_transcription + security: - ApiKey: [] @@ -33,11 +34,11 @@ paths: post: tags: - transcript - summary: Upload an audio or video file which can be transcribed. + summary: Upload a media file which can be transcribed operationId: uploadFile x-fern-sdk-group-name: files x-fern-sdk-method-name: upload - description: Upload your audio or video file directly to the AssemblyAI API if it isn't accessible via a URL already. + description: Upload your media file directly to the AssemblyAI API if it isn't accessible via a URL already. requestBody: content: application/octet-stream: @@ -76,7 +77,7 @@ paths: x-fern-sdk-method-name: create description: Create a transcript from an audio or video file that is accessible via a URL. requestBody: - description: Parameters to create a transcript. + description: Parameters to create a transcript required: true content: application/json: @@ -84,7 +85,7 @@ paths: $ref: "#/components/schemas/CreateTranscriptParameters" responses: "201": - description: Transcript created and queued for processing. + description: Transcript created and queued for processing content: application/json: schema: @@ -111,7 +112,7 @@ paths: x-fern-sdk-group-name: transcript x-fern-sdk-method-name: list operationId: listTranscripts - description: Retrieve a list of transcripts you have created. + description: Retrieve a list of transcripts you created parameters: - name: limit in: query @@ -150,7 +151,7 @@ paths: responses: "200": - description: A list of transcripts filtered by `limit` and `status` + description: A list of transcripts content: application/json: schema: @@ -225,7 +226,7 @@ paths: type: string responses: "200": - description: The deleted transcript response. + description: The deleted transcript response content: application/json: schema: @@ -249,7 +250,7 @@ paths: get: tags: - transcript - summary: Export transcript as SRT or VTT captions. + summary: Export transcript as SRT or VTT captions operationId: getSubtitles x-fern-sdk-group-name: transcript x-fern-sdk-method-name: getSubtitles @@ -263,7 +264,7 @@ paths: type: string - name: subtitle_format in: path - description: The format of the captions. + description: The format of the captions required: true schema: $ref: "#/components/schemas/SubtitleFormat" @@ -430,8 +431,8 @@ paths: get: tags: - transcript - summary: Retrieves the redacted audio object containing the status and URL to the redacted audio. - description: Retrieves the redacted audio object containing the status and URL to the redacted audio. + summary: Retrieve the redacted audio object containing the status and URL to the redacted audio. + description: Retrieve the redacted audio object containing the status and URL to the redacted audio. operationId: getRedactedAudio x-fern-sdk-group-name: transcript x-fern-sdk-method-name: getRedactedAudio @@ -445,7 +446,7 @@ paths: responses: "200": - description: The redacted audio object containing the status and URL to the redacted audio. + description: The redacted audio object containing the status and URL to the redacted audio content: application/json: schema: @@ -475,7 +476,7 @@ paths: x-fern-sdk-group-name: realtime x-fern-sdk-method-name: createTemporaryToken requestBody: - description: Parameters to create a temporary authentication token. + description: Parameters to create a temporary authentication token required: true content: application/json: @@ -483,7 +484,7 @@ paths: $ref: "#/components/schemas/CreateRealtimeTemporaryTokenParameters" responses: "200": - description: Temporary authentication token generated. + description: Temporary authentication token generated content: application/json: schema: @@ -507,13 +508,13 @@ paths: post: tags: - LeMUR - summary: Generate a custom summary from one or more transcripts. + summary: Generate a custom summary from one or more transcripts operationId: lemurSummary x-fern-sdk-group-name: lemur x-fern-sdk-method-name: summary description: Custom Summary allows you to distill a piece of audio into a few impactful sentences. You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language. requestBody: - description: Parameters to generate the summary. + description: Parameters to generate the summary required: true content: application/json: @@ -546,13 +547,13 @@ paths: post: tags: - LeMUR - summary: Create answers to one or more questions about one or more transcripts. + summary: Create answers to one or more questions about one or more transcripts operationId: lemurQuestionAnswer x-fern-sdk-group-name: lemur x-fern-sdk-method-name: questionAnswer description: Question & Answer allows you to ask free-form questions about a single transcript or a group of transcripts. The questions can be any whose answers you find useful, such as judging whether a caller is likely to become a customer or whether all items on a meeting's agenda were covered. requestBody: - description: Parameters to ask questions about the transcripts. + description: Parameters to ask questions about the transcripts required: true content: application/json: @@ -585,13 +586,13 @@ paths: post: tags: - LeMUR - summary: Extract action items from one or more meeting transcripts. + summary: Extract action items from one or more meeting transcripts operationId: lemurActionItems x-fern-sdk-group-name: lemur x-fern-sdk-method-name: actionItems description: Use LeMUR to generate a list of Action Items from a transcript requestBody: - description: Parameters to generate action items from transcripts. + description: Parameters to generate action items from transcripts required: true content: application/json: @@ -624,13 +625,13 @@ paths: post: tags: - LeMUR - summary: Ask LeMUR to use one or more transcripts with a Custom Task to handle your specialized task. + summary: Use your own prompt to run a Custom Task operationId: lemurTask x-fern-sdk-group-name: lemur x-fern-sdk-method-name: task - description: Use LeMUR to ask anything with Custom Task + description: Use your own prompt to run a Custom Task to handle your specialized task. requestBody: - description: Parameters to run the custom task. + description: Parameters to run the custom task required: true content: application/json: @@ -663,7 +664,7 @@ paths: delete: tags: - LeMUR - summary: Delete the data for a previously submitted LeMUR request. + summary: Delete the data for a previously submitted LeMUR request operationId: purgeLemurRequestData x-fern-sdk-group-name: lemur x-fern-sdk-method-name: purgeRequestData @@ -679,7 +680,7 @@ paths: type: string responses: "200": - description: LeMUR request data deleted. + description: LeMUR request data deleted content: application/json: schema: @@ -781,7 +782,7 @@ components: type: integer Timestamp: - description: Timestamp containing a start and end property in milliseconds. + description: Timestamp containing a start and end property in milliseconds type: object additionalProperties: false properties: @@ -806,40 +807,42 @@ components: description: | The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages). The default value is 'en_us'. - $ref: "#/components/schemas/TranscriptLanguageCode" + oneOf: + - $ref: "#/components/schemas/TranscriptLanguageCode" + - type: "null" punctuate: - description: Enable Automatic Punctuation, can be true or false. + description: Enable Automatic Punctuation, can be true or false type: boolean format_text: - description: Enable Text Formatting, can be true or false. + description: Enable Text Formatting, can be true or false type: boolean dual_channel: - description: Enable [Dual Channel](https://assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) transcription, can be true or false. + description: Enable [Dual Channel](https://assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) transcription, can be true or false type: boolean webhook_url: - description: The URL to which we send webhooks upon trancription completion, if provided in the transcription request. + description: The URL to which AssemblyAI send webhooks upon trancription completion type: string webhook_auth_header_name: - description: The header name which should be sent back with webhook calls, if provided in the transcription request. + description: The header name which should be sent back with webhook calls type: [string, "null"] default: null webhook_auth_header_value: - description: Defaults to null. Optionally allows a user to specify a header name and value to send back with a webhook call for added security. + description: Specify a header name and value to send back with a webhook call for added security type: [string, "null"] default: null auto_highlights: - description: Whether Key Phrases was enabled in the transcription request, either true or false + description: Whether Key Phrases is enabled, either true or false type: boolean audio_start_from: - description: The point in time, in milliseconds, to begin transcription from in your media file + description: The point in time, in milliseconds, to begin transcribing in your media file type: integer audio_end_at: @@ -847,17 +850,17 @@ components: type: integer word_boost: - description: The list of custom vocabulary to boost transcription probability for, if provided in the transcription request. + description: The list of custom vocabulary to boost transcription probability for type: array items: type: string boost_param: - description: The word boost parameter value, if provided in the transcription request. + description: The word boost parameter value $ref: "#/components/schemas/TranscriptBoostParam" filter_profanity: - description: Filter profanity from the transcribed text, can be true or false. + description: Filter profanity from the transcribed text, can be true or false type: boolean redact_pii: @@ -881,14 +884,16 @@ components: redact_pii_sub: description: The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. - $ref: "#/components/schemas/SubstitutionPolicy" + oneOf: + - $ref: "#/components/schemas/SubstitutionPolicy" + - type: "null" speaker_labels: description: Enable [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization), can be true or false type: boolean speakers_expected: - description: Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details. + description: Tell the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details. type: [integer, "null"] default: null @@ -901,7 +906,7 @@ components: type: boolean language_detection: - description: Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) was enabled in the transcription request, either true or false. + description: Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) is enabled, either true or false type: boolean custom_spelling: @@ -911,7 +916,7 @@ components: $ref: "#/components/schemas/TranscriptCustomSpelling" disfluencies: - description: Transcribe Filler Words, like "umm", in your media file; can be true or false. + description: Transcribe Filler Words, like "umm", in your media file; can be true or false type: boolean sentiment_analysis: @@ -951,11 +956,11 @@ components: $ref: "#/components/schemas/SummaryType" custom_topics: - description: Whether custom topics was enabled in the transcription request, either true or false + description: Whether custom topics is enabled, either true or false type: boolean topics: - description: The list of custom topics provided if custom topics was enabled in the transcription request + description: The list of custom topics provided, if custom topics is enabled type: array items: type: string @@ -995,7 +1000,7 @@ components: TranscriptBoostParam: type: string - description: The word boost parameter value, if provided in the transcription request. + description: The word boost parameter value enum: - low - default @@ -1054,7 +1059,7 @@ components: - speaker SubstitutionPolicy: - type: [string, "null"] + type: string description: The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. enum: - entity_type @@ -1092,7 +1097,7 @@ components: - banking_information TranscriptLanguageCode: - type: [string, "null"] + type: string description: | The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages). The default value is 'en_us'. @@ -1121,7 +1126,7 @@ components: TranscriptStatus: type: string - description: The status of your transcription. Possible values are queued, processing, completed, or error. + description: The status of your transcript. Possible values are queued, processing, completed, or error. enum: - queued - processing @@ -1133,157 +1138,93 @@ components: processing: description: The audio file is being processed by the API. completed: - description: The transcription job has been completed successfully. + description: The transcript job has been completed successfully. error: description: An error occurred while processing the audio file. - Transcript: + BaseTranscript: description: A transcript object type: object additionalProperties: false properties: id: - description: The unique identifier of your transcription + description: The unique identifier of your transcript type: string - language_model: - description: The language model that was used for the transcription + description: The language model that was used for the transcript type: string deprecated: true - acoustic_model: - description: The acoustic model that was used for the transcription + description: The acoustic model that was used for the transcript type: string deprecated: true - status: - description: The status of your transcription. Possible values are queued, processing, completed, or error. + description: The status of your transcript. Possible values are queued, processing, completed, or error. $ref: "#/components/schemas/TranscriptStatus" - language_code: description: | The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/Concepts/supported_languages). The default value is 'en_us'. $ref: "#/components/schemas/TranscriptLanguageCode" - audio_url: description: The URL of the media that was transcribed type: string - - text: - description: The textual transcript of your media file - type: [string, "null"] - - words: - description: | - An array of temporally-sequential word objects, one for each word in the transcript. - See [Speech recognition](https://www.assemblyai.com/docs/Models/speech_recognition) for more information. - type: [array, "null"] - items: - $ref: "#/components/schemas/TranscriptWord" - - utterances: - description: | - When dual_channel or speaker_labels is enabled, a list of turn-by-turn utterance objects. - See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more information. - type: [array, "null"] - items: - $ref: "#/components/schemas/TranscriptUtterance" - - confidence: - description: The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence) - type: [number, "null"] - format: double - minimum: 0 - maximum: 1 - - audio_duration: - description: The duration of this transcript object's media file, in seconds - type: [number, "null"] - format: float - punctuate: - description: Whether Automatic Punctuation was enabled in the transcription request, either true or false. + description: Whether Automatic Punctuation is enabled, either true or false type: [boolean, "null"] - format_text: - description: Whether Text Formatting was enabled in the transcription request, either true or false + description: Whether Text Formatting is enabled, either true or false type: [boolean, "null"] - dual_channel: - description: Whether [Dual channel transcription](https://www.assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) was enabled in the transcription request, either true or false + description: Whether [Dual channel transcription](https://www.assemblyai.com/docs/Models/speech_recognition#dual-channel-transcription) is enabled, either true or false type: [boolean, "null"] - webhook_url: - description: The URL to which we send webhooks upon trancription completion, if provided in the transcription request + description: The URL to which we send webhooks upon trancription completion type: [string, "null"] - - webhook_status_code: - description: The status code we received from your server when delivering your webhook, if a webhook URL was provided in the transcription request - type: [integer, "null"] - webhook_auth: - description: Whether webhook authentication details were provided in the transcription request + description: Whether webhook authentication details were provided type: boolean - webhook_auth_header_name: - description: The header name which should be sent back with webhook calls, if provided in the transcription request + description: The header name which should be sent back with webhook calls type: [string, "null"] - speed_boost: - description: Whether speed boost was enabled in the transcription request + description: Whether speed boost is enabled type: [boolean, "null"] deprecated: true - auto_highlights: - description: Whether Key Phrases was enabled in the transcription request, either true or false + description: Whether Key Phrases is enabled, either true or false type: boolean - - auto_highlights_result: - description: | - An array of results for the Key Phrases model, if it was enabled during the transcription request. - See [Key phrases](https://www.assemblyai.com/docs/Models/key_phrases) for more information. - $ref: "#/components/schemas/AutoHighlightsResult" - audio_start_from: - description: The point in time, in milliseconds, in the file at which the transcription was started, if provided in the transcription request + description: The point in time, in milliseconds, in the file at which the transcription was started type: [integer, "null"] - audio_end_at: - description: The point in time, in milliseconds, in the file at which the transcription was terminated, if provided in the transcription request + description: The point in time, in milliseconds, in the file at which the transcription was terminated type: [integer, "null"] - word_boost: - description: The list of custom vocabulary to boost transcription probability for, if provided in the transcription request + description: The list of custom vocabulary to boost transcription probability for type: array items: type: string - boost_param: - description: The word boost parameter value, if provided in the transcription request + description: The word boost parameter value type: [string, "null"] - filter_profanity: - description: Whether [Profanity Filtering](https://www.assemblyai.com/docs/Models/speech_recognition#profanity-filtering) was enabled in the transcription request, either true or false + description: Whether [Profanity Filtering](https://www.assemblyai.com/docs/Models/speech_recognition#profanity-filtering) is enabled, either true or false type: [boolean, "null"] - redact_pii: - description: Whether [PII Redaction](https://www.assemblyai.com/docs/Models/pii_redaction) was enabled in the transcription request, either true or false + description: Whether [PII Redaction](https://www.assemblyai.com/docs/Models/pii_redaction) is enabled, either true or false type: boolean - redact_pii_audio: description: | - Whether a redacted version of the audio file was generated (enabled or disabled in the transcription request), + Whether a redacted version of the audio file was generated, either true or false. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more information. type: [boolean, "null"] - redact_pii_audio_quality: description: | - The audio quality of the PII-redacted audio file, if enabled in the transcription request. + The audio quality of the PII-redacted audio file, if redact_pii_audio is enabled. See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more information. type: [string, "null"] - redact_pii_policies: description: | The list of PII Redaction policies that were enabled, if PII Redaction is enabled. @@ -1291,136 +1232,60 @@ components: type: [array, "null"] items: $ref: "#/components/schemas/PiiPolicy" - redact_pii_sub: description: The replacement logic for detected PII, can be "entity_type" or "hash". See [PII redaction](https://www.assemblyai.com/docs/Models/pii_redaction) for more details. $ref: "#/components/schemas/SubstitutionPolicy" - speaker_labels: - description: Enable [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization), can be true or false + description: Whether [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) is enabled, can be true or false type: [boolean, "null"] - speakers_expected: - description: Defaults to null. Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details. + description: Tell the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more details. type: [integer, "null"] - content_safety: - description: Enable [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation), can be true or false + description: Whether [Content Moderation](https://www.assemblyai.com/docs/Models/content_moderation) is enabled, can be true or false type: [boolean, "null"] - - content_safety_labels: - description: | - An array of results for the Content Moderation model, if it was enabled during the transcription request. - See [Content moderation](https://www.assemblyai.com/docs/Models/content_moderation) for more information. - $ref: "#/components/schemas/ContentSafetyLabelsResult" - iab_categories: - description: Enable [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification), can be true or false + description: Whether [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) is enabled, can be true or false type: [boolean, "null"] - - iab_categories_result: - description: | - The result of the Topic Detection model, if it was enabled during the transcription request. - See [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) for more information. - type: [object, "null"] - required: - - status - - results - - summary - properties: - status: - description: Will be either success, or unavailable in the rare case that the Content Moderation model failed. - $ref: "#/components/schemas/AudioIntelligenceModelStatus" - results: - description: An array of results for the Topic Detection model. - type: array - items: - $ref: "#/components/schemas/TopicDetectionResult" - summary: - description: The overall relevance of topic to the entire audio file - type: object - additionalProperties: - type: number - format: double - minimum: 0 - maximum: 1 - language_detection: - description: Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) was enabled in the transcription request, either true or false + description: Whether [Automatic language detection](https://www.assemblyai.com/docs/Models/speech_recognition#automatic-language-detection) is enabled, either true or false type: [boolean, "null"] - custom_spelling: description: Customize how words are spelled and formatted using to and from values type: [array, "null"] items: $ref: "#/components/schemas/TranscriptCustomSpelling" - auto_chapters: - description: Enable [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters), can be true or false + description: Whether [Auto Chapters](https://www.assemblyai.com/docs/Models/auto_chapters) is enabled, can be true or false type: [boolean, "null"] - - chapters: - description: An array of temporally sequential chapters for the audio file - type: [array, "null"] - items: - $ref: "#/components/schemas/Chapter" - summarization: - description: Whether [Summarization](https://www.assemblyai.com/docs/Models/summarization) was enabled in the transcription request, either true or false + description: Whether [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled, either true or false type: boolean - summary_type: - description: The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) was enabled in the transcription request + description: The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled type: [string, "null"] - summary_model: description: | The Summarization model used to generate the summary, - if [Summarization](https://www.assemblyai.com/docs/Models/summarization) was enabled in the transcription request - type: [string, "null"] - - summary: - description: The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) was enabled in the transcription request + if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled type: [string, "null"] - custom_topics: - description: Whether custom topics was enabled in the transcription request, either true or false + description: Whether custom topics is enabled, either true or false type: [boolean, "null"] - topics: - description: The list of custom topics provided if custom topics was enabled in the transcription request + description: The list of custom topics provided if custom topics is enabled type: array items: type: string - disfluencies: description: Transcribe Filler Words, like "umm", in your media file; can be true or false type: [boolean, "null"] - sentiment_analysis: - description: Enable [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis), can be true or false + description: Whether [Sentiment Analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis) is enabled, can be true or false type: [boolean, "null"] - - sentiment_analysis_results: - description: | - An array of results for the Sentiment Analysis model, if it was enabled during the transcription request. - See [Sentiment analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis) for more information. - type: [array, "null"] - items: - $ref: "#/components/schemas/SentimentAnalysisResult" - entity_detection: - description: Enable [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection), can be true or false + description: Whether [Entity Detection](https://www.assemblyai.com/docs/Models/entity_detection) is enabled, can be true or false type: [boolean, "null"] - - entities: - description: | - An array of results for the Entity Detection model, if it was enabled during the transcription request. - See [Entity detection](https://www.assemblyai.com/docs/Models/entity_detection) for more information. - type: [array, "null"] - items: - $ref: "#/components/schemas/Entity" - speech_threshold: description: | Defaults to null. Reject audio files that contain less than this fraction of speech. @@ -1429,27 +1294,238 @@ components: minimum: 0 maximum: 1 format: float - throttled: description: True while a request is throttled and false when a request is no longer throttled type: [boolean, "null"] - - error: - description: Error message of why the transcript failed - type: string required: - id - language_model - acoustic_model - status + - language_code - audio_url + - punctuate + - format_text + - dual_channel + - webhook_url - webhook_auth + - webhook_auth_header_name + - speed_boost - auto_highlights + - audio_start_from + - audio_end_at + - word_boost + - boost_param + - filter_profanity - redact_pii + - redact_pii_audio + - redact_pii_audio_quality + - redact_pii_policies + - redact_pii_sub + - speaker_labels + - speakers_expected + - content_safety + - iab_categories + - language_detection + - custom_spelling + - auto_chapters - summarization + - summary_type + - summary_model + - custom_topics + - topics + - disfluencies + - sentiment_analysis + - entity_detection + - speech_threshold + - throttled + + TopicDetectionModelResult: + description: | + The result of the Topic Detection model, if it is enabled. + See [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) for more information. + type: object + required: + - status + - results + - summary + properties: + status: + description: The status of the Topic Detection model. Either success, or unavailable in the rare case that the model failed. + $ref: "#/components/schemas/AudioIntelligenceModelStatus" + results: + description: An array of results for the Topic Detection model + type: array + items: + $ref: "#/components/schemas/TopicDetectionResult" + summary: + description: The overall relevance of topic to the entire audio file + type: object + additionalProperties: + type: number + format: double + minimum: 0 + maximum: 1 + + Transcript: + oneOf: + - $ref: "#/components/schemas/QueuedTranscript" + - $ref: "#/components/schemas/ProcessingTranscript" + - $ref: "#/components/schemas/CompletedTranscript" + - $ref: "#/components/schemas/ErrorTranscript" + discriminator: + propertyName: status + mapping: + queued: "#/components/schemas/QueuedTranscript" + processing: "#/components/schemas/ProcessingTranscript" + completed: "#/components/schemas/CompletedTranscript" + error: "#/components/schemas/ErrorTranscript" + + QueuedTranscript: + description: A transcript object that is queued for transcription + allOf: + - $ref: "#/components/schemas/BaseTranscript" + - type: object + properties: + status: + description: The status of your transcript, currently queued. + type: string + const: queued + required: [status] + + ProcessingTranscript: + description: A transcript object that is being processed + allOf: + - $ref: "#/components/schemas/BaseTranscript" + - type: object + properties: + status: + description: The status of your transcript, currently processing. + type: string + const: processing + required: [status] + + ErrorTranscript: + description: A transcript object that failed due to an error + allOf: + - $ref: "#/components/schemas/BaseTranscript" + - type: object + additionalProperties: false + properties: + status: + description: The status of your transcript, currently error. + type: string + const: error + error: + description: Error message of why the transcript failed + type: string + required: [status, error] + + CompletedTranscript: + description: A transcript object that is completed + allOf: + - $ref: "#/components/schemas/BaseTranscript" + - type: object + additionalProperties: false + properties: + status: + description: The status of your transcript, currently completed. + type: string + const: completed + text: + description: The textual transcript of your media file + type: string + words: + description: | + An array of temporally-sequential word objects, one for each word in the transcript. + See [Speech recognition](https://www.assemblyai.com/docs/Models/speech_recognition) for more information. + type: array + items: + $ref: "#/components/schemas/TranscriptWord" + utterances: + description: | + When dual_channel or speaker_labels is enabled, a list of turn-by-turn utterance objects. + See [Speaker diarization](https://www.assemblyai.com/docs/Models/speaker_diarization) for more information. + type: [array, "null"] + items: + $ref: "#/components/schemas/TranscriptUtterance" + confidence: + description: The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence) + type: number + format: double + minimum: 0 + maximum: 1 + audio_duration: + description: The duration of this transcript object's media file, in seconds + type: number + format: float + webhook_status_code: + description: The status code we received from your server when delivering your webhook, if a webhook URL was provided + type: [integer, "null"] + auto_highlights_result: + description: | + An array of results for the Key Phrases model, if it is enabled. + See [Key phrases](https://www.assemblyai.com/docs/Models/key_phrases) for more information. + oneOf: + - $ref: "#/components/schemas/AutoHighlightsResult" + - type: "null" + content_safety_labels: + description: | + An array of results for the Content Moderation model, if it is enabled. + See [Content moderation](https://www.assemblyai.com/docs/Models/content_moderation) for more information. + oneOf: + - $ref: "#/components/schemas/ContentSafetyLabelsResult" + - type: "null" + iab_categories_result: + description: | + The result of the Topic Detection model, if it is enabled. + See [Topic Detection](https://www.assemblyai.com/docs/Models/iab_classification) for more information. + oneOf: + - $ref: "#/components/schemas/TopicDetectionModelResult" + - type: "null" + chapters: + description: An array of temporally sequential chapters for the audio file + type: [array, "null"] + items: + $ref: "#/components/schemas/Chapter" + summary: + description: The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/Models/summarization) is enabled + type: [string, "null"] + sentiment_analysis_results: + description: | + An array of results for the Sentiment Analysis model, if it is enabled. + See [Sentiment analysis](https://www.assemblyai.com/docs/Models/sentiment_analysis) for more information. + type: [array, "null"] + items: + $ref: "#/components/schemas/SentimentAnalysisResult" + entities: + description: | + An array of results for the Entity Detection model, if it is enabled. + See [Entity detection](https://www.assemblyai.com/docs/Models/entity_detection) for more information. + type: [array, "null"] + items: + $ref: "#/components/schemas/Entity" + required: + - status + - text + - words + - utterances + - confidence + - audio_duration + - webhook_status_code + - auto_highlights_result + - content_safety_labels + - iab_categories_result + - chapters + - summary + - sentiment_analysis_results + - entities ContentSafetyLabelsResult: - type: [object, "null"] + description: | + An array of results for the Content Moderation model, if it is enabled. + See [Content moderation](https://www.assemblyai.com/docs/Models/content_moderation) for more information. + type: object required: - status - results @@ -1457,7 +1533,7 @@ components: - severity_score_summary properties: status: - description: Will be either success, or unavailable in the rare case that the Content Moderation model failed. + description: The status of the Content Moderation model. Either success, or unavailable in the rare case that the model failed. $ref: "#/components/schemas/AudioIntelligenceModelStatus" results: type: array @@ -1625,7 +1701,7 @@ components: description: Social Security Number or equivalent SentimentAnalysisResult: - description: The result of the sentiment analysis model. + description: The result of the sentiment analysis model type: object additionalProperties: false required: @@ -1664,7 +1740,7 @@ components: - NEGATIVE TopicDetectionResult: - description: The result of the topic detection model. + description: The result of the topic detection model type: object additionalProperties: false required: @@ -1732,7 +1808,7 @@ components: description: The transcript of the section flagged by the Content Moderation model type: string labels: - description: An array of objects, one per sensitive topic that was detected in the section + description: An array of safety labels, one per sensitive topic that was detected in the section type: array items: $ref: "#/components/schemas/ContentSafetyLabel" @@ -1771,9 +1847,9 @@ components: AutoHighlightsResult: description: | - An array of results for the Key Phrases model, if it was enabled during the transcription request. + An array of results for the Key Phrases model, if it is enabled. See [Key phrases](https://www.assemblyai.com/docs/Models/key_phrases) for more information. - type: [object, "null"] + type: object required: - results properties: @@ -2035,7 +2111,7 @@ components: additionalProperties: false properties: expires_in: - description: The amount of time until the token expires in seconds. + description: The amount of time until the token expires in seconds type: integer minimum: 60 required: [expires_in] @@ -2052,7 +2128,7 @@ components: AudioIntelligenceModelStatus: type: string - description: Will be either success, or unavailable in the rare case that the model failed. + description: Either success, or unavailable in the rare case that the model failed enum: - success - unavailable @@ -2063,13 +2139,13 @@ components: properties: request_id: type: string - description: The ID of the LeMUR request + description: The ID of the deletion request of the LeMUR request request_id_to_purge: type: string - description: The ID of the deletion request of the LeMUR request + description: The ID of the LeMUR request to purge the data for deleted: type: boolean - description: Whether the request data was deleted. + description: Whether the request data was deleted required: - request_id - request_id_to_purge @@ -2092,7 +2168,7 @@ components: additionalProperties: false properties: response: - description: The response generated by LeMUR. + description: The response generated by LeMUR type: string required: [response] @@ -2103,7 +2179,7 @@ components: additionalProperties: false properties: response: - description: The answers generated by LeMUR and their questions. + description: The answers generated by LeMUR and their questions type: array items: $ref: "#/components/schemas/LemurQuestionAnswer" @@ -2111,14 +2187,14 @@ components: LemurQuestionAnswer: type: object - description: An answer generated by LeMUR and its question. + description: An answer generated by LeMUR and its question additionalProperties: false properties: question: - description: The question for LeMUR to answer. + description: The question for LeMUR to answer type: string answer: - description: The answer generated by LeMUR. + description: The answer generated by LeMUR type: string required: [question, answer] @@ -2129,7 +2205,7 @@ components: additionalProperties: false properties: response: - description: The response generated by LeMUR. + description: The response generated by LeMUR type: string required: [response] @@ -2140,7 +2216,7 @@ components: additionalProperties: false properties: response: - description: The response generated by LeMUR. + description: The response generated by LeMUR type: string required: [response] @@ -2162,7 +2238,7 @@ components: final_model: $ref: "#/components/schemas/LemurModel" max_output_size: - description: Max output size in tokens. Up to 4000 allowed. + description: Max output size in tokens, up to 4000 type: integer temperature: description: | @@ -2193,7 +2269,7 @@ components: additionalProperties: false properties: questions: - description: A list of questions to ask. + description: A list of questions to ask type: array items: $ref: "#/components/schemas/LemurQuestion" @@ -2208,7 +2284,7 @@ components: description: The question you wish to ask. For more complex questions use default model. type: string context: - description: Any context about the transcripts you wish to provide. This can be a string, or free-form JSON. + description: Any context about the transcripts you wish to provide. This can be a string or any object. oneOf: - type: string - type: object