Class: AssemblyAI::TranscriptsClient

Inherits:
Object
  • Object
show all
Defined in:
lib/assemblyai/transcripts/polling_client.rb,
lib/assemblyai/transcripts/client.rb,
lib/assemblyai/transcripts/list_by_url_client.rb

Overview

:nodoc:

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(request_client:) ⇒ TranscriptsClient

Parameters:



29
30
31
32
 
# File 'lib/assemblyai/transcripts/client.rb', line 29

def initialize(request_client:)
  # @type [RequestClient]
  @request_client = request_client
end

Instance Attribute Details

#request_client ⇒ Object (readonly)

Returns the value of attribute request_client.



25
26
27
 
# File 'lib/assemblyai/transcripts/client.rb', line 25

def request_client
  @request_client
end

Instance Method Details

#delete(transcript_id:, request_options: nil) ⇒ Transcripts::Transcript

Delete the transcript

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • request_options (RequestOptions) (defaults to: nil)

Returns:



182
183
184
185
186
187
188
189
190
 
# File 'lib/assemblyai/transcripts/client.rb', line 182

def delete(transcript_id:, request_options: nil)
  response = @request_client.conn.delete do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}"
  end
  Transcripts::Transcript.from_json(json_object: response.body)
end

#get(transcript_id:, request_options: nil) ⇒ Transcripts::Transcript

Get the transcript resource. The transcript is ready when the “status” is “completed”.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • request_options (RequestOptions) (defaults to: nil)

Returns:



167
168
169
170
171
172
173
174
175
 
# File 'lib/assemblyai/transcripts/client.rb', line 167

def get(transcript_id:, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}"
  end
  Transcripts::Transcript.from_json(json_object: response.body)
end

#get_paragraphs(transcript_id:, request_options: nil) ⇒ Transcripts::ParagraphsResponse

Get the transcript split by paragraphs. The API will attempt to semantically segment your transcript into paragraphs to create more reader-friendly transcripts.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • request_options (RequestOptions) (defaults to: nil)

Returns:



233
234
235
236
237
238
239
240
241
 
# File 'lib/assemblyai/transcripts/client.rb', line 233

def get_paragraphs(transcript_id:, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}/paragraphs"
  end
  Transcripts::ParagraphsResponse.from_json(json_object: response.body)
end

#get_redacted_audio(transcript_id:, request_options: nil) ⇒ Transcripts::RedactedAudioResponse

Retrieve the redacted audio object containing the status and URL to the redacted audio.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • request_options (RequestOptions) (defaults to: nil)

Returns:



265
266
267
268
269
270
271
272
273
 
# File 'lib/assemblyai/transcripts/client.rb', line 265

def get_redacted_audio(transcript_id:, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}/redacted-audio"
  end
  Transcripts::RedactedAudioResponse.from_json(json_object: response.body)
end

#get_sentences(transcript_id:, request_options: nil) ⇒ Transcripts::SentencesResponse

Get the transcript split by sentences. The API will attempt to semantically segment the transcript into sentences to create more reader-friendly transcripts.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • request_options (RequestOptions) (defaults to: nil)

Returns:



218
219
220
221
222
223
224
225
226
 
# File 'lib/assemblyai/transcripts/client.rb', line 218

def get_sentences(transcript_id:, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}/sentences"
  end
  Transcripts::SentencesResponse.from_json(json_object: response.body)
end

#get_subtitles(transcript_id:, subtitle_format:, chars_per_caption: nil, request_options: nil) ⇒ String

Export your transcript in SRT or VTT format, to be plugged into a video player for subtitles and closed captions.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • subtitle_format (Transcripts::SubtitleFormat) —

    The format of the captions

  • chars_per_caption (Integer) (defaults to: nil) —

    The maximum number of characters per caption

  • request_options (RequestOptions) (defaults to: nil)

Returns:

  • (String) 


199
200
201
202
203
204
205
206
207
208
209
210
211
 
# File 'lib/assemblyai/transcripts/client.rb', line 199

def get_subtitles(transcript_id:, subtitle_format:, chars_per_caption: nil, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.params = {
      **(request_options&.additional_query_parameters || {}),
      "chars_per_caption": chars_per_caption
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}/#{subtitle_format}"
  end
  response.body
end

#list(limit: nil, status: nil, created_on: nil, before_id: nil, after_id: nil, throttled_only: nil, request_options: nil) ⇒ Transcripts::TranscriptList

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.

Parameters:

  • limit (Integer) (defaults to: nil) —

    Maximum amount of transcripts to retrieve

  • status (Transcripts::TranscriptStatus) (defaults to: nil) —

    Filter by transcript status

  • created_on (String) (defaults to: nil) —

    Only get transcripts created on this date

  • before_id (String) (defaults to: nil) —

    Get transcripts that were created before this transcript ID

  • after_id (String) (defaults to: nil) —

    Get transcripts that were created after this transcript ID

  • throttled_only (Boolean) (defaults to: nil) —

    Only get throttled transcripts, overrides the status filter

  • request_options (RequestOptions) (defaults to: nil)

Returns:



45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
 
# File 'lib/assemblyai/transcripts/client.rb', line 45

def list(limit: nil, status: nil, created_on: nil, before_id: nil, after_id: nil, throttled_only: nil,
         request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.params = {
      **(request_options&.additional_query_parameters || {}),
      "limit": limit,
      "status": status,
      "created_on": created_on,
      "before_id": before_id,
      "after_id": after_id,
      "throttled_only": throttled_only
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript"
  end
  Transcripts::TranscriptList.from_json(json_object: response.body)
end

#list_by_url(url: nil, request_options: nil) ⇒ Transcripts::TranscriptList

Retrieve a list of transcripts you created, this is used for pagination to easily retrieve the next page of transcripts

Examples:

Retrieve the next page of results

client = AssemblyAI::Client.new(api_key: "YOUR_API_KEY")
transcript_list = client.transcripts.list(limit: 1)
client.transcripts.list_by_url(url: transcript_list.page_details.next_url)

Parameters:

  • url (String) (defaults to: nil) —

    The URL to retrieve the transcript list from

  • request_options (RequestOptions) (defaults to: nil)

Returns:



20
21
22
23
24
25
26
27
28
29
 
# File 'lib/assemblyai/transcripts/list_by_url_client.rb', line 20

def list_by_url(url: nil, request_options: nil)
  url = "#{@request_client.get_url(request_options: request_options)}/v2/transcript" if url.nil?
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.url url
  end
  Transcripts::TranscriptList.from_json(json_object: response.body)
end

#submit(audio_url:, speech_model: nil, language_code: nil, punctuate: nil, format_text: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, language_detection: nil, custom_spelling: nil, disfluencies: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, additional_properties: nil, request_options: nil) ⇒ Transcripts::Transcript

Create a transcript from an audio or video file that is accessible via a URL.

Parameters:

  • speech_model (Transcripts::SpeechModel) (defaults to: nil)
  • language_code (Transcripts::TranscriptLanguageCode) (defaults to: nil)
  • punctuate (Boolean) (defaults to: nil) —

    Enable Automatic Punctuation, can be true or false

  • format_text (Boolean) (defaults to: nil) —

    Enable Text Formatting, can be true or false

  • dual_channel (Boolean) (defaults to: nil) —

    Enable [Dual Channel](www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) transcription, can be true or false.

  • webhook_url (String) (defaults to: nil) —

    The URL to which AssemblyAI send webhooks upon trancription completion

  • webhook_auth_header_name (String) (defaults to: nil) —

    The header name which should be sent back with webhook calls

  • webhook_auth_header_value (String) (defaults to: nil) —

    Specify a header name and value to send back with a webhook call for added security

  • auto_highlights (Boolean) (defaults to: nil) —

    Whether Key Phrases is enabled, either true or false

  • audio_start_from (Integer) (defaults to: nil) —

    The point in time, in milliseconds, to begin transcribing in your media file

  • audio_end_at (Integer) (defaults to: nil) —

    The point in time, in milliseconds, to stop transcribing in your media file

  • word_boost (Array<String>) (defaults to: nil) —

    The list of custom vocabulary to boost transcription probability for

  • boost_param (Transcripts::TranscriptBoostParam) (defaults to: nil) —

    The word boost parameter value

  • filter_profanity (Boolean) (defaults to: nil) —

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

  • redact_pii (Boolean) (defaults to: nil) —

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

  • redact_pii_audio (Boolean) (defaults to: nil) —

    Generate a copy of the original media file with spoken PII “beeped” out, can be true or false. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_audio_quality (Transcripts::RedactPiiAudioQuality) (defaults to: nil) —

    Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_policies (Array<Transcripts::PiiPolicy>) (defaults to: nil) —

    The list of PII Redaction policies to enable. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_sub (Transcripts::SubstitutionPolicy) (defaults to: nil)
  • speaker_labels (Boolean) (defaults to: nil) —

    Enable [Speaker diarization](www.assemblyai.com/docs/models/speaker-diarization), can be true or false

  • speakers_expected (Integer) (defaults to: nil) —

    Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](www.assemblyai.com/docs/models/speaker-diarization) for more details.

  • content_safety (Boolean) (defaults to: nil) —

    Enable [Content Moderation](www.assemblyai.com/docs/models/content-moderation), can be true or false

  • content_safety_confidence (Integer) (defaults to: nil) —

    The confidence threshold for content moderation. Values must be between 25 and 100.

  • iab_categories (Boolean) (defaults to: nil) —

    Enable [Topic Detection](www.assemblyai.com/docs/models/topic-detection), can be true or false

  • language_detection (Boolean) (defaults to: nil) —

    Whether [Automatic language detection](www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) was enabled in the transcription request, either true or false.

  • custom_spelling (Array<Hash>) (defaults to: nil) —

    Customize how words are spelled and formatted using to and from valuesRequest of type Array<Transcripts::TranscriptCustomSpelling>, as a Hash

    • :from (Array<String>)

    • :to (String)

  • disfluencies (Boolean) (defaults to: nil) —

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

  • sentiment_analysis (Boolean) (defaults to: nil) —

    Enable [Sentiment Analysis](www.assemblyai.com/docs/models/sentiment-analysis), can be true or false

  • auto_chapters (Boolean) (defaults to: nil) —

    Enable [Auto Chapters](www.assemblyai.com/docs/models/auto-chapters), can be true or false

  • entity_detection (Boolean) (defaults to: nil) —

    Enable [Entity Detection](www.assemblyai.com/docs/models/entity-detection), can be true or false

  • speech_threshold (Float) (defaults to: nil) —

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

  • summarization (Boolean) (defaults to: nil) —

    Enable [Summarization](www.assemblyai.com/docs/models/summarization), can be true or false

  • summary_model (Transcripts::SummaryModel) (defaults to: nil) —

    The model to summarize the transcript

  • summary_type (Transcripts::SummaryType) (defaults to: nil) —

    The type of summary

  • custom_topics (Boolean) (defaults to: nil) —

    Whether custom topics is enabled, either true or false

  • topics (Array<String>) (defaults to: nil) —

    The list of custom topics provided, if custom topics is enabled

  • additional_properties (OpenStruct) (defaults to: nil) —

    Additional properties unmapped to the current class definition

  • audio_url (String) —

    The URL of the audio or video file to transcribe.

  • request_options (RequestOptions) (defaults to: nil)

Returns:



110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
 
# File 'lib/assemblyai/transcripts/client.rb', line 110

def submit(audio_url:, speech_model: nil, language_code: nil, punctuate: nil, format_text: nil, dual_channel: nil,
           webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, language_detection: nil, custom_spelling: nil, disfluencies: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, additional_properties: nil, request_options: nil)
  response = @request_client.conn.post do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.body = {
      **(request_options&.additional_body_parameters || {}),
      speech_model: speech_model,
      language_code: language_code,
      punctuate: punctuate,
      format_text: format_text,
      dual_channel: dual_channel,
      webhook_url: webhook_url,
      webhook_auth_header_name: webhook_auth_header_name,
      webhook_auth_header_value: webhook_auth_header_value,
      auto_highlights: auto_highlights,
      audio_start_from: audio_start_from,
      audio_end_at: audio_end_at,
      word_boost: word_boost,
      boost_param: boost_param,
      filter_profanity: filter_profanity,
      redact_pii: redact_pii,
      redact_pii_audio: redact_pii_audio,
      redact_pii_audio_quality: redact_pii_audio_quality,
      redact_pii_policies: redact_pii_policies,
      redact_pii_sub: redact_pii_sub,
      speaker_labels: speaker_labels,
      speakers_expected: speakers_expected,
      content_safety: content_safety,
      content_safety_confidence: content_safety_confidence,
      iab_categories: iab_categories,
      language_detection: language_detection,
      custom_spelling: custom_spelling,
      disfluencies: disfluencies,
      sentiment_analysis: sentiment_analysis,
      auto_chapters: auto_chapters,
      entity_detection: entity_detection,
      speech_threshold: speech_threshold,
      summarization: summarization,
      summary_model: summary_model,
      summary_type: summary_type,
      custom_topics: custom_topics,
      topics: topics,
      additional_properties: additional_properties,
      audio_url: audio_url
    }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript"
  end
  Transcripts::Transcript.from_json(json_object: response.body)
end

#transcribe(audio_url:, speech_model: nil, language_code: nil, punctuate: nil, format_text: nil, dual_channel: nil, webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, language_detection: nil, custom_spelling: nil, disfluencies: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, additional_properties: nil, request_options: nil, polling_options: Transcripts::PollingOptions.new) ⇒ Transcripts::Transcript

Create a transcript from an audio or video file that is accessible via a URL. .transcribe polls for completion of the transcription, while the .submit function does not.

Parameters:

  • speech_model (Transcripts::SpeechModel) (defaults to: nil)
  • language_code (Transcripts::TranscriptLanguageCode) (defaults to: nil)
  • punctuate (Boolean) (defaults to: nil) —

    Enable Automatic Punctuation, can be true or false

  • format_text (Boolean) (defaults to: nil) —

    Enable Text Formatting, can be true or false

  • dual_channel (Boolean) (defaults to: nil) —

    Enable [Dual Channel](www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription) transcription, can be true or false.

  • webhook_url (String) (defaults to: nil) —

    The URL to which AssemblyAI send webhooks upon trancription completion

  • webhook_auth_header_name (String) (defaults to: nil) —

    The header name which should be sent back with webhook calls

  • webhook_auth_header_value (String) (defaults to: nil) —

    Specify a header name and value to send back with a webhook call for added security

  • auto_highlights (Boolean) (defaults to: nil) —

    Whether Key Phrases is enabled, either true or false

  • audio_start_from (Integer) (defaults to: nil) —

    The point in time, in milliseconds, to begin transcribing in your media file

  • audio_end_at (Integer) (defaults to: nil) —

    The point in time, in milliseconds, to stop transcribing in your media file

  • word_boost (Array<String>) (defaults to: nil) —

    The list of custom vocabulary to boost transcription probability for

  • boost_param (Transcripts::TranscriptBoostParam) (defaults to: nil) —

    The word boost parameter value

  • filter_profanity (Boolean) (defaults to: nil) —

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

  • redact_pii (Boolean) (defaults to: nil) —

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

  • redact_pii_audio (Boolean) (defaults to: nil) —

    Generate a copy of the original media file with spoken PII “beeped” out, can be true or false. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_audio_quality (Transcripts::RedactPiiAudioQuality) (defaults to: nil) —

    Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_policies (Array<Transcripts::PiiPolicy>) (defaults to: nil) —

    The list of PII Redaction policies to enable. See [PII redaction](www.assemblyai.com/docs/models/pii-redaction) for more details.

  • redact_pii_sub (Transcripts::SubstitutionPolicy) (defaults to: nil)
  • speaker_labels (Boolean) (defaults to: nil) —

    Enable [Speaker diarization](www.assemblyai.com/docs/models/speaker-diarization), can be true or false

  • speakers_expected (Integer) (defaults to: nil) —

    Tells the speaker label model how many speakers it should attempt to identify, up to 10. See [Speaker diarization](www.assemblyai.com/docs/models/speaker-diarization) for more details.

  • content_safety (Boolean) (defaults to: nil) —

    Enable [Content Moderation](www.assemblyai.com/docs/models/content-moderation), can be true or false

  • content_safety_confidence (Integer) (defaults to: nil) —

    The confidence threshold for content moderation. Values must be between 25 and 100.

  • iab_categories (Boolean) (defaults to: nil) —

    Enable [Topic Detection](www.assemblyai.com/docs/models/topic-detection), can be true or false

  • language_detection (Boolean) (defaults to: nil) —

    Whether [Automatic language detection](www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection) was enabled in the transcription request, either true or false.

  • custom_spelling (Array<Hash>) (defaults to: nil) —

    Customize how words are spelled and formatted using to and from valuesRequest of type Array<Transcripts::TranscriptCustomSpelling>, as a Hash

    • :from (Array<String>)

    • :to (String)

  • disfluencies (Boolean) (defaults to: nil) —

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

  • sentiment_analysis (Boolean) (defaults to: nil) —

    Enable [Sentiment Analysis](www.assemblyai.com/docs/models/sentiment-analysis), can be true or false

  • auto_chapters (Boolean) (defaults to: nil) —

    Enable [Auto Chapters](www.assemblyai.com/docs/models/auto-chapters), can be true or false

  • entity_detection (Boolean) (defaults to: nil) —

    Enable [Entity Detection](www.assemblyai.com/docs/models/entity-detection), can be true or false

  • speech_threshold (Float) (defaults to: nil) —

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

  • summarization (Boolean) (defaults to: nil) —

    Enable [Summarization](www.assemblyai.com/docs/models/summarization), can be true or false

  • summary_model (Transcripts::SummaryModel) (defaults to: nil) —

    The model to summarize the transcript

  • summary_type (Transcripts::SummaryType) (defaults to: nil) —

    The type of summary

  • custom_topics (Boolean) (defaults to: nil) —

    Whether custom topics is enabled, either true or false

  • topics (Array<String>) (defaults to: nil) —

    The list of custom topics provided, if custom topics is enabled

  • additional_properties (OpenStruct) (defaults to: nil) —

    Additional properties unmapped to the current class definition

  • audio_url (String) —

    The URL of the audio or video file to transcribe.

  • request_options (RequestOptions) (defaults to: nil)
  • polling_options (Transcripts::PollingOptions) (defaults to: Transcripts::PollingOptions.new) —

    Configuration options for polling requests.

Returns:



73
74
75
76
77
78
 
# File 'lib/assemblyai/transcripts/polling_client.rb', line 73

def transcribe(audio_url:, speech_model: nil, language_code: nil, punctuate: nil, format_text: nil, dual_channel: nil,
               webhook_url: nil, webhook_auth_header_name: nil, webhook_auth_header_value: nil, auto_highlights: nil, audio_start_from: nil, audio_end_at: nil, word_boost: nil, boost_param: nil, filter_profanity: nil, redact_pii: nil, redact_pii_audio: nil, redact_pii_audio_quality: nil, redact_pii_policies: nil, redact_pii_sub: nil, speaker_labels: nil, speakers_expected: nil, content_safety: nil, content_safety_confidence: nil, iab_categories: nil, language_detection: nil, custom_spelling: nil, disfluencies: nil, sentiment_analysis: nil, auto_chapters: nil, entity_detection: nil, speech_threshold: nil, summarization: nil, summary_model: nil, summary_type: nil, custom_topics: nil, topics: nil, additional_properties: nil, request_options: nil, polling_options: Transcripts::PollingOptions.new)
  transcript = submit(audio_url: audio_url, speech_model: speech_model, language_code: language_code, punctuate: punctuate, format_text: format_text, dual_channel: dual_channel,
                      webhook_url: webhook_url, webhook_auth_header_name: webhook_auth_header_name, webhook_auth_header_value: webhook_auth_header_value, auto_highlights: auto_highlights, audio_start_from: audio_start_from, audio_end_at: audio_end_at, word_boost: word_boost, boost_param: boost_param, filter_profanity: filter_profanity, redact_pii: redact_pii, redact_pii_audio: redact_pii_audio, redact_pii_audio_quality: redact_pii_audio_quality, redact_pii_policies: redact_pii_policies, redact_pii_sub: redact_pii_sub, speaker_labels: speaker_labels, speakers_expected: speakers_expected, content_safety: content_safety, content_safety_confidence: content_safety_confidence, iab_categories: iab_categories, language_detection: language_detection, custom_spelling: custom_spelling, disfluencies: disfluencies, sentiment_analysis: sentiment_analysis, auto_chapters: auto_chapters, entity_detection: entity_detection, speech_threshold: speech_threshold, summarization: summarization, summary_model: summary_model, summary_type: summary_type, custom_topics: custom_topics, topics: topics, additional_properties: additional_properties, request_options: request_options)
  wait_until_ready(transcript_id: transcript.id, polling_options: polling_options)
end

#wait_until_ready(transcript_id:, polling_options: Transcripts::PollingOptions.new) ⇒ Transcripts::Transcript

Wait until the transcript is ready. The transcript is ready when the “status” is “completed”.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • polling_options (PollingOptions) (defaults to: Transcripts::PollingOptions.new)

Returns:



85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/assemblyai/transcripts/polling_client.rb', line 85

def wait_until_ready(transcript_id:, polling_options: Transcripts::PollingOptions.new)
  start_time = Time.now
  timeout_in_seconds = polling_options.timeout / 1000 if polling_options.timeout.positive?
  loop do
    transcript = get(transcript_id: transcript_id)
    if transcript.status == Transcripts::TranscriptStatus::COMPLETED || transcript.status == Transcripts::TranscriptStatus::ERROR
      return transcript
    elsif polling_options.timeout.positive? && Time.now - start_time > timeout_in_seconds
      raise StandardError, "Polling timeout"
    end

    sleep polling_options.interval / 1000
  end
end

#word_search(transcript_id:, words: nil, request_options: nil) ⇒ Transcripts::WordSearchResponse

Search through the transcript for a specific set of keywords. You can search for individual words, numbers, or phrases containing up to five words or numbers.

Parameters:

  • transcript_id (String) —

    ID of the transcript

  • words (String) (defaults to: nil) —

    Keywords to search for

  • request_options (RequestOptions) (defaults to: nil)

Returns:



249
250
251
252
253
254
255
256
257
258
 
# File 'lib/assemblyai/transcripts/client.rb', line 249

def word_search(transcript_id:, words: nil, request_options: nil)
  response = @request_client.conn.get do |req|
    req.options.timeout = request_options.timeout_in_seconds unless request_options&.timeout_in_seconds.nil?
    req.headers["Authorization"] = request_options.api_key unless request_options&.api_key.nil?
    req.headers = { **req.headers, **(request_options&.additional_headers || {}) }.compact
    req.params = { **(request_options&.additional_query_parameters || {}), "words": words }.compact
    req.url "#{@request_client.get_url(request_options: request_options)}/v2/transcript/#{transcript_id}/word-search"
  end
  Transcripts::WordSearchResponse.from_json(json_object: response.body)
end