{"openapi":"3.0.0","info":{"description":"Speech-to-text transcription and audio intelligence platform with speaker diarization and sentiment analysis","version":[{"name":"v2","value":"v2"},{"name":"v3","value":"v3"}]},"servers":[{"description":"Speech-to-text transcription and audio intelligence platform with speaker diarization and sentiment analysis","url":"https://api.apirails.com/assemblyai"}],"paths":{"/v2/transcript/:id":{"delete":{"tags":["Transcript"],"parameters":[{"name":"id","in":"path","description":"The unique identifier of your transcription","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/delete","api_endpoint":"https://api.assemblyai.com/v2/transcript/:id"},"summary":"Deleting transcript","description":"Deleting transcript.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{}},"example":{}}}}}},"/v2/transcript":{"post":{"tags":["Transcript"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/submit","api_endpoint":"https://api.assemblyai.com/v2/transcript"},"summary":"Transcribe audio","description":"Create a transcript from a media file that is accessible via a URL.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"audio_end_at":{"type":"number","description":"The point in time, in milliseconds, to stop transcribing in your media file"},"audio_start_from":{"type":"number","description":"Returns transcripts that were created before a specific transcript ID"},"audio_url":{"type":"string","description":"The URL of the audio or video file to transcribe.","required":true},"auto_chapters":{"type":"boolean","description":"Enable Auto Chapters, can be true or false","enum":[true,false]},"auto_highlights":{"type":"boolean","description":"Enable Key Phrases, either true or false","enum":[true,false]},"boost_param":{"type":"string","description":"Boost Param"},"content_safety":{"type":"boolean","description":"Enable Content Moderation, can be true or false","enum":[true,false]},"content_safety_confidence":{"type":"number","description":"The confidence threshold for the Content Moderation model. Values must be between 25 and 100."},"custom_spelling":{"type":"array","description":"Customize how words are spelled and formatted using to and from values","items":{"type":"string"}},"custom_topics":{"type":"boolean","description":"Enable custom topics, either true or false","enum":[true,false]},"disfluencies":{"type":"boolean","description":"Transcribe Filler Words, like “umm”, in your media file; can be true or false","enum":[true,false]},"dual_channel":{"type":"boolean","description":"Deprecated: Enable Dual Channel transcription, can be true or false.","enum":[true,false]},"entity_detection":{"type":"boolean","description":"Enable Entity Detection, can be true or false","enum":[true,false]},"filter_profanity":{"type":"boolean","description":"Filter profanity from the transcribed text, can be true or false","enum":[true,false]},"format_text":{"type":"boolean","description":"Enable Text Formatting, can be true or false","enum":[true,false]},"iab_categories":{"type":"boolean","description":"Enable Topic Detection, can be true or false","enum":[true,false]},"language_code":{"type":"object","description":"The language of your audio file. Possible values are found in Supported Languages. The default value is ‘en_us’.","properties":{}},"language_confidence_threshold":{"type":"number","description":"The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0."},"language_detection":{"type":"boolean","description":"Enable Automatic language detection, either true or false.","enum":[true,false]},"multichannel":{"type":"boolean","description":"Enable Multichannel transcription, can be true or false.","enum":[true,false]},"punctuate":{"type":"boolean","description":"Enable Automatic Punctuation, can be true or false.","enum":[true,false]},"redact_pii":{"type":"boolean","description":"Redact PII from the transcribed text using the Redact PII model, can be true or false.","enum":[true,false]},"redact_pii_audio":{"type":"boolean","description":"Generate a copy of the original media file with spoken PII 'beeped' out, can be true or false.","enum":[true,false]},"redact_pii_audio_quality":{"type":"object","description":"Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav.","properties":{}},"redact_pii_policies":{"type":"array","description":"The list of PII Redaction policies to enable.","items":{"type":"string"}},"redact_pii_sub":{"type":"object","description":"The replacement logic for detected PII, can be 'entity_name' or 'hash'.","properties":{}},"sentiment_analysis":{"type":"boolean","description":"Enable Sentiment Analysis, can be true or false.","enum":[true,false]},"speaker_labels":{"type":"boolean","description":"Enable Speaker diarization, can be true or false.","enum":[true,false]},"speakers_expected":{"type":"number","description":"Tells the speaker label model how many speakers it should attempt to identify, up to 10."},"speech_model":{"type":"object","description":"The speech model to use for the transcription.","properties":{}},"speech_threshold":{"type":"number","description":"Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive."},"summarization":{"type":"boolean","description":"Enable Summarization, can be true or false.","enum":[true,false]},"summary_model":{"type":"object","description":"The model to summarize the transcript.","properties":{}},"summary_type":{"type":"object","description":"The type of summary.","properties":{}},"topics":{"type":"array","description":"The list of custom topics.","items":{"type":"string"}},"webhook_auth_header_name":{"type":"string","description":"The header name to be sent with the transcript completed or failed webhook requests."},"webhook_auth_header_value":{"type":"string","description":"The header value to send back with the transcript completed or failed webhook requests for added security."},"webhook_url":{"type":"string","description":"The URL to which we send webhook requests. We sends two different types of webhook requests. One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled."},"word_boost":{"type":"array","description":"The list of custom vocabulary to boost transcription probability for.","items":{"type":"string"}}}},"example":{"audio_end_at":"","audio_start_from":"","audio_url":"","auto_chapters":"","auto_highlights":"","boost_param":"","content_safety":"","content_safety_confidence":"","custom_spelling":[],"custom_topics":"","disfluencies":"","dual_channel":"","entity_detection":"","filter_profanity":"","format_text":"","iab_categories":"","language_code":{},"language_confidence_threshold":"","language_detection":"","multichannel":"","punctuate":"","redact_pii":"","redact_pii_audio":"","redact_pii_audio_quality":{},"redact_pii_policies":[],"redact_pii_sub":{},"sentiment_analysis":"","speaker_labels":"","speakers_expected":"","speech_model":{},"speech_threshold":"","summarization":"","summary_model":{},"summary_type":{},"topics":[],"webhook_auth_header_name":"","webhook_auth_header_value":"","webhook_url":"","word_boost":[]}}}}},"get":{"tags":["Transcript"],"parameters":[{"name":"after_id","in":"query","description":"Get transcripts that were created after this transcript ID.","schema":{"type":"string","example":""}},{"name":"before_id","in":"query","description":"Get transcripts that were created before this transcript ID.","schema":{"type":"string","example":""}},{"name":"created_on","in":"query","description":"Only get transcripts created on this date.","schema":{"type":"string","example":""}},{"name":"limit","in":"query","description":"Maximum amount of transcripts to retrieve.","schema":{"type":"number","example":""}},{"name":"status","in":"query","description":"Filter by transcript status.","schema":{"type":"object","example":""}},{"name":"throttled_only","in":"query","description":"Only get throttled transcripts, overrides the status filter.","schema":{"type":"boolean","example":"","items":{"type":"string","enum":[true,false]}}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/list","api_endpoint":"https://api.assemblyai.com/v2/transcript"},"summary":"List transcripts","description":"Retrieve a list of transcripts you created. Transcripts are sorted from newest to oldest. The previous URL always points to a page with older transcripts.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"ID of the transcript","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id"},"summary":"Get transcript","description":"Get the transcript resource. The transcript is ready when the “status” is “completed”.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/sentences":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"ID of the transcript","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-sentences","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/sentences"},"summary":"Get sentences in transcript","description":"Get the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/:subtitle_format":{"get":{"tags":["Transcript"],"parameters":[{"name":"id","in":"path","description":"The unique identifier of your transcription","required":true,"schema":{"type":"string","example":""}},{"name":"subtitle_format","in":"path","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-subtitles","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/:subtitle_format"},"summary":"Get subtitles for transcript","description":"Export your completed transcripts in SRT (srt) or VTT (vtt) format, which can be used for subtitles and closed captions in videos.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/redacted-audio":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"transcript_id","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-redacted-audio","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/redacted-audio"},"summary":"Get redacted audio","description":"If you enable PII redaction, get the redacted audio, as described in the Create a redacted audio file section.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/paragraphs":{"get":{"tags":["Transcript"],"parameters":[{"name":"id","in":"path","description":"The unique identifier of your transcription","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-paragraphs","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/paragraphs"},"summary":"Get paragraphs in transcript","description":"Optionally, after your transcript is complete, get the paragraphs using its id.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/words":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"ID of the transcript","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-words","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/words"},"summary":"Get word timestamps in transcript","description":"Get the transcript with word-level timestamps. Each word in the transcript will have a start and end time in milliseconds.","security":[{"bearerAuth":[]}]}},"/v2/transcript/:transcript_id/chapters":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"ID of the transcript","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/get-chapters","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/chapters"},"summary":"Get chapters in transcript","description":"Get the transcript split by chapters. Chapters are automatically detected sections of the transcript.","security":[{"bearerAuth":[]}]}},"/v2/upload":{"post":{"tags":["Files"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/files/upload","api_endpoint":"https://api.assemblyai.com/v2/upload"},"summary":"Upload a media file","description":"Upload a media file to AssemblyAI’s servers.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":false,"content":{"multipart/form-data":{"schema":{"type":"object","required":[],"properties":{}},"example":{}}}}}},"/v2/transcript/:transcript_id/word-search":{"get":{"tags":["Transcript"],"parameters":[{"name":"transcript_id","in":"path","description":"ID of the transcript.","required":true,"schema":{"type":"string","example":""}},{"name":"words","in":"query","description":"Keywords to search for","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/transcripts/word-search","api_endpoint":"https://api.assemblyai.com/v2/transcript/:transcript_id/word-search"},"summary":"Search words in transcript","description":"Search through the transcript for keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.","security":[{"bearerAuth":[]}]}},"/lemur/v3/generate/task":{"post":{"tags":["LeMUR"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/task","api_endpoint":"https://api.assemblyai.com/lemur/v3/generate/task"},"summary":"Run a task using LeMUR","description":"Use the LeMUR task endpoint to input your own LLM prompt.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"context":{"type":"string","description":"Context to provide the model."},"final_model":{"type":"object","description":"The model that is used for the final prompt after compression is performed.","properties":{}},"input_text":{"type":"string","description":"Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000."},"max_output_size":{"type":"number","description":"Defaults to 2000. Max output size in tokens."},"prompt":{"type":"string","description":"Your text to prompt the model to produce a desired output, including any context you want to pass into the model."},"temperature":{"type":"number","description":"The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative."},"transcript_ids":{"type":"array","description":"A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower.","items":{"type":"string"}}}},"example":{"context":"","final_model":{},"input_text":"","max_output_size":"","prompt":"","temperature":"","transcript_ids":[]}}}}}},"/lemur/v3/generate/summary":{"post":{"tags":["LeMUR"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/summary","api_endpoint":"https://api.assemblyai.com/lemur/v3/generate/summary"},"summary":"Summarize a transcript using LeMUR","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.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"answer_format":{"type":"string","description":"This can be any text."},"context":{"type":"string","description":"Context to provide the model."},"final_model":{"type":"object","description":"The model that is used for the final prompt after compression is performed.","properties":{}},"input_text":{"type":"string","description":"Custom formatted transcript data. Maximum size is the context limit of the selected model"},"max_output_size":{"type":"number","description":"Defaults to 2000. Max output size in tokens."},"temperature":{"type":"number","description":"The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative."},"transcript_ids":{"type":"array","description":"A list of completed transcripts with text.","items":{"type":"string"}}}},"example":{"answer_format":"","context":"","final_model":{},"input_text":"","max_output_size":"","temperature":"","transcript_ids":[]}}}}}},"/lemur/v3/generate/question-answer":{"post":{"tags":["LeMUR"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/question-answer","api_endpoint":"https://api.assemblyai.com/lemur/v3/generate/question-answer"},"summary":"Ask questions using LeMUR","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.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"context":{"type":"string","description":"Context to provide the model."},"final_model":{"type":"object","description":"The model that is used for the final prompt after compression is performed.","properties":{}},"input_text":{"type":"string","description":"Custom formatted transcript data. Maximum size is the context limit of the selected model"},"max_output_size":{"type":"number","description":"Defaults to 2000. Max output size in tokens."},"questions":{"type":"array","description":"A list of questions to ask","items":{"type":"string"}},"temperature":{"type":"number","description":"The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative."},"transcript_ids":{"type":"array","description":"A list of completed transcripts with text.","items":{"type":"string"}}}},"example":{"context":"","final_model":{},"input_text":"","max_output_size":"","questions":[],"temperature":"","transcript_ids":[]}}}}}},"/lemur/v3/generate/action-items":{"post":{"tags":["LeMUR"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/action-items","api_endpoint":"https://api.assemblyai.com/lemur/v3/generate/action-items"},"summary":"Extract action items","description":"Use LeMUR to generate a list of action items from a transcript.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"answer_format":{"type":"array","description":"How you want the action items to be returned. This can be any text. Defaults to “Bullet Points”.","items":{"type":"string"}},"context":{"type":"string","description":"Context to provide the model."},"final_model":{"type":"object","description":"The model that is used for the final prompt after compression is performed.","properties":{}},"input_text":{"type":"string","description":"Custom formatted transcript data. Maximum size is the context limit of the selected model"},"max_output_size":{"type":"number","description":"Defaults to 2000. Max output size in tokens."},"temperature":{"type":"number","description":"The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative."},"transcript_ids":{"type":"array","description":"A list of completed transcripts with text.","items":{"type":"string"}}}},"example":{"answer_format":[],"context":"","final_model":{},"input_text":"","max_output_size":"","temperature":"","transcript_ids":[]}}}}}},"/lemur/v3/:request_id":{"get":{"tags":["LeMUR"],"parameters":[{"name":"request_id","in":"path","description":"The ID of the LeMUR request you previously made. This would be found in the response of the original request.","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/get-response","api_endpoint":"https://api.assemblyai.com/lemur/v3/:request_id"},"summary":"Retrieve LeMUR response","description":"Retrieve a LeMUR response that was previously generated.","security":[{"bearerAuth":[]}]},"delete":{"tags":["LeMUR"],"parameters":[{"name":"request_id","in":"path","description":"The ID of the LeMUR request you previously made. This would be found in the response of the original request.","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/lemur/purge-request-data","api_endpoint":"https://api.assemblyai.com/lemur/v3/:request_id"},"summary":"Purge LeMUR request data","description":"Delete the data for a previously submitted LeMUR request. The LLM response data, as well as any context provided in the original request will be removed.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{}},"example":{}}}}}},"/v2/realtime/token":{"post":{"tags":["Streaming"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/streaming/create-temporary-token","api_endpoint":"https://api.assemblyai.com/v2/realtime/token"},"summary":"Create temporary authentication token for Streaming STT","description":"Create a temporary authentication token for Streaming Speech-to-Text.","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"expires_in":{"type":"number","description":"The amount of time until the token expires in seconds","required":true}}},"example":{"expires_in":""}}}}}},"/v2/stream":{"get":{"tags":["Streaming"],"parameters":[{"name":"disable_partial_transcripts","in":"query","description":"Set to true to not receive partial transcripts. Defaults to false.","schema":{"type":"boolean","example":"","items":{"type":"string","enum":[true,false]}}},{"name":"enable_extra_session_information","in":"query","description":"Set to true to receive the SessionInformation message before the session ends. Defaults to false.","schema":{"type":"boolean","example":"","items":{"type":"string","enum":[true,false]}}},{"name":"encoding","in":"query","description":"The encoding of the audio data. Defaults to pcm_s16le.","schema":{"type":"object","example":""}},{"name":"sample_rate","in":"query","description":"The sample rate of the streamed audio.","schema":{"type":"number","example":""}},{"name":"token","in":"query","description":"Authenticate using a generated temporary token.","schema":{"type":"string","example":""}},{"name":"word_boost","in":"query","description":"Add up to 2500 characters of custom vocabulary.","schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://www.assemblyai.com/docs/api-reference/streaming/realtime","api_endpoint":"wss://api.assemblyai.com/v2/realtime/ws"},"summary":"Streaming Speech-to-Text","description":"Streaming Speech-to-Text.","security":[{"bearerAuth":[]}]}}},"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer"}}},"security":[{"bearerAuth":[]}]}