> ## Documentation Index > Fetch the complete documentation index at: https://gcore.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get AI task result > This is the single method to check the execution status of an AI task, and obtain the result of any type of AI task. Based on the results of processing, the “result” field will contain an answer corresponding to the type of the initially created task: - ASR: Transcribe video - ASR: Translate subtitles - CM: Sports detection - CM: Not Safe For Work (NSFW) content detection - CM: Soft nudity detection - CM: Hard nudity detection - CM: Objects recognition (soon) - etc... (see other methods from /ai/ domain) A queue is used to process videos. The waiting time depends on the total number of requests in the system, so sometimes you will have to wait. Statuses: - PENDING – the task is received and it is pending for available resources - STARTED – processing has started - SUCCESS – processing has completed successfully - FAILURE – processing failed - REVOKED – processing was cancelled by the user (or the system) - RETRY – the task execution failed due to internal reasons, the task is queued for re-execution (up to 3 times) Each task is processed in sub-stages, for example, original language is first determined in a video, and then transcription is performed. In such cases, the video processing status may change from "STARTED" to "PENDING", and back. This is due to waiting for resources for a specific processing sub-stage. In this case, the overall percentage "progress" of video processing will reflect the full picture. The result data is stored for 1 month, after which it is deleted. For billing conditions see the corresponding methods in /ai/ domain. The task is billed only after successful completion of the task and transition to "SUCCESS" status. ## OpenAPI ````yaml /api-reference/services_documented/streaming_api.yaml get /streaming/ai/tasks/{task_id} openapi: 3.1.0 info: title: Gcore OpenAPI – Streaming API description: >- This OpenAPI is an aggregated OpenAPI specification that unifies all Gcore products into a single file. It covers Cloud, CDN, DNS, WAAP, DDoS Protection, Object Storage, Streaming, and FastEdge services. version: '2026-05-14T07:00:22.640261+00:00' servers: - url: https://api.gcore.com security: - APIKey: [] tags: - name: AI x-displayName: AI - name: Broadcasts x-displayName: Broadcasts - name: Directories x-displayName: Directories - name: Overlays x-displayName: Overlays - name: Players x-displayName: Players - name: Playlists x-displayName: Playlists - name: QualitySets x-displayName: QualitySets - name: Restreams x-displayName: Restreams - name: Streaming Statistics x-displayName: Statistics - name: Streams x-displayName: Streams - name: Subtitles x-displayName: Subtitles - name: Videos x-displayName: Videos paths: /streaming/ai/tasks/{task_id}: get: tags: - AI summary: Get AI task result description: >- This is the single method to check the execution status of an AI task, and obtain the result of any type of AI task. Based on the results of processing, the “result” field will contain an answer corresponding to the type of the initially created task: - ASR: Transcribe video - ASR: Translate subtitles - CM: Sports detection - CM: Not Safe For Work (NSFW) content detection - CM: Soft nudity detection - CM: Hard nudity detection - CM: Objects recognition (soon) - etc... (see other methods from /ai/ domain) A queue is used to process videos. The waiting time depends on the total number of requests in the system, so sometimes you will have to wait. Statuses: - PENDING – the task is received and it is pending for available resources - STARTED – processing has started - SUCCESS – processing has completed successfully - FAILURE – processing failed - REVOKED – processing was cancelled by the user (or the system) - RETRY – the task execution failed due to internal reasons, the task is queued for re-execution (up to 3 times) Each task is processed in sub-stages, for example, original language is first determined in a video, and then transcription is performed. In such cases, the video processing status may change from "STARTED" to "PENDING", and back. This is due to waiting for resources for a specific processing sub-stage. In this case, the overall percentage "progress" of video processing will reflect the full picture. The result data is stored for 1 month, after which it is deleted. For billing conditions see the corresponding methods in /ai/ domain. The task is billed only after successful completion of the task and transition to "SUCCESS" status. operationId: get_ai_task parameters: - name: task_id in: path required: true schema: type: string description: >- ID of the task to get status of execution or result. This value is taken from the response of the initial AI task creation method. responses: '200': description: Result of AI task execution content: application/json: schema: $ref: '#/components/schemas/ai_results' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/notfound' '422': description: >- This is advanced functionality; to enable it, contact your manager or the Support Team. content: application/json: schema: $ref: '#/components/schemas/upgraderequired' x-codeSamples: - lang: Python source: |- import os from gcore import Gcore client = Gcore( api_key=os.environ.get("GCORE_API_KEY"), # This is the default and can be omitted ) ai_task = client.streaming.ai_tasks.get( "task_id", ) print(ai_task) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/G-Core/gcore-go\"\n\t\"github.com/G-Core/gcore-go/option\"\n)\n\nfunc main() {\n\tclient := gcore.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\taiTask, err := client.Streaming.AITasks.Get(context.TODO(), \"task_id\")\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", aiTask)\n}\n" components: schemas: ai_results: allOf: - $ref: '#/components/schemas/ai_task_base' properties: processing_time: type: object properties: started_at: type: string description: Video processing start time. Format is date time in ISO 8601 completed_at: type: string description: Video processing end time. Format is date time in ISO 8601 default: null total_time_sec: type: number format: decimal description: Duration of video processing in seconds default: null result: oneOf: - $ref: '#/components/schemas/ai_results_transcribe' - $ref: '#/components/schemas/ai_results_contentmoderation_sport' - $ref: '#/components/schemas/ai_results_contentmoderation_nsfw' - $ref: '#/components/schemas/ai_results_contentmoderation_hardnudity' - $ref: '#/components/schemas/ai_results_contentmoderation_softnudity' - $ref: '#/components/schemas/ai_results_failure' default: null example: task_id: aafe70c6-0000-0000-0000-327b65f7670f task_data: {} progress: 100 status: SUCCESS processing_time: started_at: '2024-07-13T12:30:00.000Z' completed_at: '2024-07-13T12:31:02.900Z' total_time_sec: 62.901 result: {} notfound: allOf: - $ref: '#/components/schemas/badrequest' - example: status: 404 error: >- Not Found. Entity you are looking for was not found, please check the initial parameters upgraderequired: type: object properties: error: type: string description: >- This is advanced functionality; to enable it, contact your manager or support service. example: error: Feature is disabled. Contact support to enable. ai_task_base: type: object properties: task_id: type: string format: uuid description: ID of the AI task status: type: string description: >- Status of processing the AI task. See GET /ai/results method for description. enum: - PENDING - STARTED - SUCCESS - FAILURE - REVOKED - RETRY progress: type: integer default: null description: >- Percentage of task completed. A value greater than 0 means that it has been taken into operation and is being processed. task_name: type: string description: Type of AI task enum: - content-moderation - transcription task_data: oneOf: - $ref: '#/components/schemas/ai_transcribe' - $ref: '#/components/schemas/ai_contentmoderation_nsfw' - $ref: '#/components/schemas/ai_contentmoderation_hardnudity' - $ref: '#/components/schemas/ai_contentmoderation_softnudity' - $ref: '#/components/schemas/ai_contentmoderation_sport' description: >- The object will correspond to the task type that was specified in the original request. There will be one object for transcription, another for searching for nudity, and so on. ai_results_transcribe: type: object properties: speech_detected: type: boolean description: >- Determines whether speech was detected or not. Please note: If the task is in "SUCCESS" status and speech was not found in the entire file, then "false" will be indicated here and the ```subtitles``` field will be empty. concatenated_text: type: string description: >- Full text of the analyzed video. The value is unstructured, unformatted text. subtitles: type: array items: type: object properties: start_time: type: string description: >- Start time of the phrase when it is heard in the video. Format is "HH:mm:ss.fff". end_time: type: string description: >- End time of the phrase, when it ends in the video. Format is "HH:mm:ss.fff". text: type: string description: >- A complete phrase that sounds during a specified period of time. description: >- An array of phrases divided into time intervals, in the format "json". Suitable when you need to display the result in chronometric form, or transfer the text for further processing. vttContent: type: string description: Auto generated subtitles in WebVTT format. languages: type: array items: type: string description: >- An array of language codes that were discovered and/or used in transcription. If the audio or subtitle language was explicitly specified in the initial parameters, it will be copied here. For automatic detection the identified languages will be displayed here. Also please note that for multilingual audio, the first 5 languages are displayed in order of frequency of use. example: concatenated_text: >- Come on team, we mustn't dilly dally when there's so much nature to see! I was thinking, we should call our class project, Fungi in a Forest! subtitles: - start_time: '00:00:00.009' end_time: '00:00:03.689' text: >- Come on team, we mustn't dilly dally when there's so much nature to see! - start_time: '00:00:04.129' end_time: '00:00:08.169' text: >- I was thinking, we should call our class project, Fungi in a Forest! vttContent: >+ WEBVTT 1 00:00:00.009 --> 00:00:03.689 Come on team, we mustn't dilly dally when there's so much nature to see! 2 00:00:04.129 --> 00:00:08.169 I was thinking, we should call our class project, Fungi in a Forest! languages: - eng ai_results_contentmoderation_sport: type: object properties: sport_detected: type: boolean description: A boolean value whether any sports were detected detection_results: type: array items: type: string description: Array of detected sports enum: - archery - arm wrestling - playing badminton - playing baseball - basketball dunk - bowling - boxing punch - boxing speed bag - catching or throwing baseball - catching or throwing softball - cricket - curling - disc golfing - dodgeball - fencing - football - golf chipping - golf driving - golf putting - hitting baseball - hockey stop - ice skating - javelin throw - juggling soccer ball - kayaking - kicking field goal - kicking soccer ball - playing cricket - playing field hockey - playing ice hockey - playing kickball - playing lacrosse - playing ping pong - playing polo - playing squash or racquetball - playing tennis - playing volleyball - pole vault - riding a bike - riding or walking with horse - roller skating - rowing - sailing - shooting goal (soccer) - skateboarding - skiing frames: type: array items: type: object properties: frame-number: type: integer description: Video frame number where activity was found label: type: string description: Type of detected activity confidence: type: number format: decimal description: Percentage of probability of identifying the activity example: sport_detected: true detection_results: - football - playing tennis frames: - frame-number: 4 label: football score: 0.95 - frame-number: 100 label: playing tennis score: 0.5 ai_results_contentmoderation_nsfw: type: object properties: nsfw_detected: type: boolean description: A boolean value whether any Not Safe For Work content was detected detection_results: type: array items: type: string description: Array of detected category enum: - nsfw frames: type: array items: type: object properties: frame-number: type: integer description: Video frame number where object was found label: type: string description: Type of detected object confidence: type: number format: decimal description: Percentage of probability of identifying the object example: porn_detected: true detection_results: - nsfw frames: - frame-number: 4 label: nsfw score: '1.0' - frame-number: 100 label: nsfw score: 0.51 ai_results_contentmoderation_hardnudity: type: object properties: porn_detected: type: boolean description: A boolean value whether any nudity was detected detection_results: type: array items: type: string description: Array of detected nudity category enum: - ANUS_EXPOSED - BUTTOCKS_EXPOSED - FEMALE_BREAST_EXPOSED - FEMALE_GENITALIA_EXPOSED - MALE_BREAST_EXPOSED - MALE_GENITALIA_EXPOSED frames: type: array items: type: object properties: frame-number: type: integer description: Video frame number where object was found label: type: string description: Type of detected object confidence: type: number format: decimal description: Percentage of probability of identifying the object example: porn_detected: true detection_results: - FEMALE_BREAST_EXPOSED - MALE_GENITALIA_EXPOSED frames: - frame-number: 4 label: FEMALE_BREAST_EXPOSED score: 0.95 - frame-number: 100 label: MALE_GENITALIA_EXPOSED score: 0.51 ai_results_contentmoderation_softnudity: type: object properties: porn_detected: type: boolean description: A boolean value whether any nudity and other body part was detected detection_results: type: array items: type: string description: Array of detected nudity or body part category enum: - ANUS_COVERED - ANUS_EXPOSED - ARMPITS_COVERED - ARMPITS_EXPOSED - BELLY_COVERED - BELLY_EXPOSED - BUTTOCKS_COVERED - BUTTOCKS_EXPOSED - FACE_FEMALE - FACE_MALE - FEET_COVERED - FEET_EXPOSED - FEMALE_BREAST_COVERED - FEMALE_BREAST_EXPOSED - FEMALE_GENITALIA_COVERED - FEMALE_GENITALIA_EXPOSED - MALE_BREAST_EXPOSED - MALE_GENITALIA_EXPOSED frames: type: array items: type: object properties: frame-number: type: integer description: Video frame number where object was found label: type: string description: Type of detected object confidence: type: number format: decimal description: Percentage of probability of identifying the object example: porn_detected: true detection_results: - FACE_FEMALE - FACE_MALE frames: - frame-number: 4 label: FACE_FEMALE score: 0.95 - frame-number: 100 label: FACE_MALE score: 0.51 ai_results_failure: type: object required: - error properties: error: type: string example: error: 'Unsupported file type: https://domain.com/video.zip' badrequest: type: object properties: status: type: integer description: Error number error: type: string description: Error message example: status: 400 error: >- Bad Request response status code indicates that the server cannot or will not process the request due to something that is perceived to be a client error (for example, malformed request syntax, invalid request message framing, or deceptive request routing). ai_transcribe: type: object required: - url - task_name properties: task_name: type: string description: Name of the task to be performed enum: - transcription url: type: string description: >- URL to the MP4 file to analyse. File must be publicly accessible via HTTP/HTTPS. audio_language: type: string description: >- Language in original audio (transcription only). This value is used to determine the language from which to transcribe. If this is not set, the system will run auto language identification and the subtitles will be in the detected language. The method also works based on AI analysis. It's fairly accurate, but if it's wrong, then set the language explicitly. Additionally, when this is not set, we also support recognition of alternate languages in the video (language code-switching). Language is set by 3-letter language code according to ISO-639-2 (bibliographic code). We can process languages: - 'afr': Afrikaans - 'alb': Albanian - 'amh': Amharic - 'ara': Arabic - 'arm': Armenian - 'asm': Assamese - 'aze': Azerbaijani - 'bak': Bashkir - 'baq': Basque - 'bel': Belarusian - 'ben': Bengali - 'bos': Bosnian - 'bre': Breton - 'bul': Bulgarian - 'bur': Myanmar - 'cat': Catalan - 'chi': Chinese - 'cze': Czech - 'dan': Danish - 'dut': Nynorsk - 'eng': English - 'est': Estonian - 'fao': Faroese - 'fin': Finnish - 'fre': French - 'geo': Georgian - 'ger': German - 'glg': Galician - 'gre': Greek - 'guj': Gujarati - 'hat': Haitian creole - 'hau': Hausa - 'haw': Hawaiian - 'heb': Hebrew - 'hin': Hindi - 'hrv': Croatian - 'hun': Hungarian - 'ice': Icelandic - 'ind': Indonesian - 'ita': Italian - 'jav': Javanese - 'jpn': Japanese - 'kan': Kannada - 'kaz': Kazakh - 'khm': Khmer - 'kor': Korean - 'lao': Lao - 'lat': Latin - 'lav': Latvian - 'lin': Lingala - 'lit': Lithuanian - 'ltz': Luxembourgish - 'mac': Macedonian - 'mal': Malayalam - 'mao': Maori - 'mar': Marathi - 'may': Malay - 'mlg': Malagasy - 'mlt': Maltese - 'mon': Mongolian - 'nep': Nepali - 'dut': Dutch - 'nor': Norwegian - 'oci': Occitan - 'pan': Punjabi - 'per': Persian - 'pol': Polish - 'por': Portuguese - 'pus': Pashto - 'rum': Romanian - 'rus': Russian - 'san': Sanskrit - 'sin': Sinhala - 'slo': Slovak - 'slv': Slovenian - 'sna': Shona - 'snd': Sindhi - 'som': Somali - 'spa': Spanish - 'srp': Serbian - 'sun': Sundanese - 'swa': Swahili - 'swe': Swedish - 'tam': Tamil - 'tat': Tatar - 'tel': Telugu - 'tgk': Tajik - 'tgl': Tagalog - 'tha': Thai - 'tib': Tibetan - 'tuk': Turkmen - 'tur': Turkish - 'ukr': Ukrainian - 'urd': Urdu - 'uzb': Uzbek - 'vie': Vietnamese - 'wel': Welsh - 'yid': Yiddish - 'yor': Yoruba default: null subtitles_language: type: string description: >- Indicates which language it is clearly necessary to translate into. If this is not set, the original language will be used from attribute "audio_language". Please note that: - transcription into the original language is a free procedure, - and translation from the original language into any other languages is a "translation" procedure and is paid. More details in [POST /streaming/ai/tasks#transcribe](/docs/api-reference/streaming/ai/create-ai-asr-task). Language is set by 3-letter language code according to ISO-639-2 (bibliographic code). default: null client_user_id: type: string maxLength: 256 default: null description: >- Meta parameter, designed to store your own identifier. Can be used by you to tag requests from different end-users. It is not used in any way in video processing. client_entity_data: type: string maxLength: 4096 default: null description: >- Meta parameter, designed to store your own extra information about a video entity: video source, video id, etc. It is not used in any way in video processing. For example, if an AI-task was created automatically when you uploaded a video with the AI auto-processing option (transcribing, translationing), then the ID of the associated video for which the task was performed will be explicitly indicated here. example: url: https://demo-files.gvideo.io/apidocs/spritefright-blender-cut30sec.mp4 task_name: transcription audio_language: ger ai_contentmoderation_nsfw: allOf: - $ref: '#/components/schemas/ai_contentmoderation_general' required: - category properties: category: type: string enum: - nsfw description: AI content moderation with NSFW detection algorithm example: url: https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4 task_name: content-moderation category: nsfw ai_contentmoderation_hardnudity: allOf: - $ref: '#/components/schemas/ai_contentmoderation_general' required: - category properties: category: type: string enum: - hard_nudity description: AI content moderation with "hard_nudity" algorithm stop_objects: type: string enum: - ANUS_EXPOSED - BUTTOCKS_EXPOSED - FEMALE_BREAST_EXPOSED - FEMALE_GENITALIA_EXPOSED - MALE_BREAST_EXPOSED - MALE_GENITALIA_EXPOSED description: >- Comma separated objects, and probabilities, that will cause the processing to stop immediatelly after finding. example: url: https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4 task_name: content-moderation category: hard_nudity stop_objects: >- FEMALE_GENITALIA_EXPOSED,FEMALE_BREAST_EXPOSED:0.50,BUTTOCKS_EXPOSED:0.90 ai_contentmoderation_softnudity: allOf: - $ref: '#/components/schemas/ai_contentmoderation_general' required: - category properties: category: type: string enum: - soft_nudity description: AI content moderation with "soft_nudity" algorithm stop_objects: type: string enum: - ANUS_COVERED - ANUS_EXPOSED - ARMPITS_COVERED - ARMPITS_EXPOSED - BELLY_COVERED - BELLY_EXPOSED - BUTTOCKS_COVERED - BUTTOCKS_EXPOSED - FACE_FEMALE - FACE_MALE - FEET_COVERED - FEET_EXPOSED - FEMALE_BREAST_COVERED - FEMALE_BREAST_EXPOSED - FEMALE_GENITALIA_COVERED - FEMALE_GENITALIA_EXPOSED - MALE_BREAST_EXPOSED - MALE_GENITALIA_EXPOSED description: >- Comma separated objects, and probabilities, that will cause the processing to stop immediatelly after finding. example: url: https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4 task_name: content-moderation category: soft_nudity stop_objects: BELLY_COVERED:0.9,FEMALE_GENITALIA_COVERED ai_contentmoderation_sport: allOf: - $ref: '#/components/schemas/ai_contentmoderation_general' required: - category properties: category: type: string enum: - sport description: AI content moderation with types of sports activity detection example: url: >- https://demo-files.gvideo.io/ai_demo_soccer_players_passing_the_ball.mp4 task_name: content-moderation category: sport ai_contentmoderation_general: type: object required: - url - task_name properties: task_name: type: string description: Name of the task to be performed enum: - content-moderation url: type: string description: >- URL to the MP4 file to analyse. File must be publicly accessible via HTTP/HTTPS. category: type: string description: >- Model for analysis (content-moderation only). Determines what exactly needs to be found in the video. enum: - sport - nsfw - hard_nudity - soft_nudity client_user_id: type: string maxLength: 256 default: null description: >- Meta parameter, designed to store your own identifier. Can be used by you to tag requests from different end-users. It is not used in any way in video processing. client_entity_data: type: string maxLength: 4096 default: null description: >- Meta parameter, designed to store your own extra information about a video entity: video source, video id, etc. It is not used in any way in video processing. For example, if an AI-task was created automatically when you uploaded a video with the AI auto-processing option (nudity detection, etc), then the ID of the associated video for which the task was performed will be explicitly indicated here. example: url: https://demo-files.gvideo.io/ai_demo_subtitles_nudity_detection.mp4 task_name: content-moderation category: nsfw securitySchemes: APIKey: description: >- API key for authentication. Make sure to include the word `apikey`, followed by a single space and then your token. Example: `apikey 1234$abcdef` type: apiKey in: header name: Authorization ````