elevenlabs_client 0.4.0 → 0.6.0

data/lib/elevenlabs_client/endpoints/admin/usage.rb

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  module Admin
+    class Usage
+      def initialize(client)
+        @client = client
+      end
+
+      # GET /v1/usage/character-stats
+      # Gets character usage metrics for the current user or workspace
+      # Documentation: https://elevenlabs.io/docs/api-reference/usage/get-character-stats
+      #
+      # @param start_unix [Integer] UTC Unix timestamp for the start of the usage window (in milliseconds)
+      # @param end_unix [Integer] UTC Unix timestamp for the end of the usage window (in milliseconds)
+      # @param include_workspace_metrics [Boolean] Whether to include the statistics of the entire workspace (defaults to false)
+      # @param breakdown_type [String] How to break down the information. Cannot be "user" if include_workspace_metrics is false
+      # @param aggregation_interval [String] How to aggregate usage data over time ("hour", "day", "week", "month", or "cumulative")
+      # @param aggregation_bucket_size [Integer, nil] Aggregation bucket size in seconds. Overrides the aggregation interval
+      # @param metric [String] Which metric to aggregate
+      # @return [Hash] The JSON response containing time axis and usage data
+      def get_character_stats(start_unix:, end_unix:, include_workspace_metrics: nil, breakdown_type: nil, aggregation_interval: nil, aggregation_bucket_size: nil, metric: nil)
+        endpoint = "/v1/usage/character-stats"
+        
+        params = {
+          start_unix: start_unix,
+          end_unix: end_unix
+        }
+        
+        params[:include_workspace_metrics] = include_workspace_metrics unless include_workspace_metrics.nil?
+        params[:breakdown_type] = breakdown_type if breakdown_type
+        params[:aggregation_interval] = aggregation_interval if aggregation_interval
+        params[:aggregation_bucket_size] = aggregation_bucket_size if aggregation_bucket_size
+        params[:metric] = metric if metric
+        
+        @client.get(endpoint, params)
+      end
+
+      alias_method :character_stats, :get_character_stats
+
+      private
+
+      attr_reader :client
+    end
+  end
+end

data/lib/elevenlabs_client/endpoints/admin/user.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  module Admin
+    class User
+      def initialize(client)
+        @client = client
+      end
+
+      # GET /v1/user
+      # Gets information about the user
+      # Documentation: https://elevenlabs.io/docs/api-reference/user/get-user
+      #
+      # @return [Hash] The JSON response containing user information including subscription details
+      def get_user
+        endpoint = "/v1/user"
+        @client.get(endpoint)
+      end
+
+      alias_method :user, :get_user
+      alias_method :info, :get_user
+
+      private
+
+      attr_reader :client
+    end
+  end
+end

data/lib/elevenlabs_client/endpoints/admin/voice_library.rb

@@ -0,0 +1,86 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  module Admin
+    class VoiceLibrary
+      def initialize(client)
+        @client = client
+      end
+
+      # GET /v1/shared-voices
+      # Retrieves a list of shared voices
+      # Documentation: https://elevenlabs.io/docs/api-reference/shared-voices/get-shared-voices
+      #
+      # @param page_size [Integer] How many shared voices to return at maximum. Cannot exceed 100, defaults to 30
+      # @param category [String] Voice category used for filtering ("professional", "famous", "high_quality")
+      # @param gender [String, nil] Gender used for filtering
+      # @param age [String, nil] Age used for filtering
+      # @param accent [String, nil] Accent used for filtering
+      # @param language [String, nil] Language used for filtering
+      # @param locale [String, nil] Locale used for filtering
+      # @param search [String, nil] Search term used for filtering
+      # @param use_cases [Array<String>, nil] Use-case used for filtering
+      # @param descriptives [Array<String>, nil] Descriptive terms used for filtering
+      # @param featured [Boolean] Filter featured voices (defaults to false)
+      # @param min_notice_period_days [Integer, nil] Filter voices with a minimum notice period
+      # @param include_custom_rates [Boolean, nil] Include/exclude voices with custom rates
+      # @param include_live_moderated [Boolean, nil] Include/exclude voices that are live moderated
+      # @param reader_app_enabled [Boolean] Filter voices that are enabled for the reader app (defaults to false)
+      # @param owner_id [String, nil] Filter voices by public owner ID
+      # @param sort [String, nil] Sort criteria
+      # @param page [Integer] Page number (defaults to 0)
+      # @return [Hash] The JSON response containing voices array and pagination info
+      def get_shared_voices(page_size: nil, category: nil, gender: nil, age: nil, accent: nil, language: nil, locale: nil, search: nil, use_cases: nil, descriptives: nil, featured: nil, min_notice_period_days: nil, include_custom_rates: nil, include_live_moderated: nil, reader_app_enabled: nil, owner_id: nil, sort: nil, page: nil)
+        endpoint = "/v1/shared-voices"
+        
+        params = {}
+        params[:page_size] = page_size if page_size
+        params[:category] = category if category
+        params[:gender] = gender if gender
+        params[:age] = age if age
+        params[:accent] = accent if accent
+        params[:language] = language if language
+        params[:locale] = locale if locale
+        params[:search] = search if search
+        params[:use_cases] = use_cases if use_cases
+        params[:descriptives] = descriptives if descriptives
+        params[:featured] = featured unless featured.nil?
+        params[:min_notice_period_days] = min_notice_period_days if min_notice_period_days
+        params[:include_custom_rates] = include_custom_rates unless include_custom_rates.nil?
+        params[:include_live_moderated] = include_live_moderated unless include_live_moderated.nil?
+        params[:reader_app_enabled] = reader_app_enabled unless reader_app_enabled.nil?
+        params[:owner_id] = owner_id if owner_id
+        params[:sort] = sort if sort
+        params[:page] = page if page
+        
+        @client.get(endpoint, params)
+      end
+
+      # POST /v1/voices/add/:public_user_id/:voice_id
+      # Add a shared voice to your collection of voices
+      # Documentation: https://elevenlabs.io/docs/api-reference/shared-voices/add-shared-voice
+      #
+      # @param public_user_id [String] Public user ID used to publicly identify ElevenLabs users
+      # @param voice_id [String] ID of the voice to be used
+      # @param new_name [String] The name that identifies this voice
+      # @return [Hash] The JSON response containing the voice_id
+      def add_shared_voice(public_user_id:, voice_id:, new_name:)
+        endpoint = "/v1/voices/add/#{public_user_id}/#{voice_id}"
+        
+        body = {
+          new_name: new_name
+        }
+        
+        @client.post(endpoint, body)
+      end
+
+      alias_method :shared_voices, :get_shared_voices
+      alias_method :list_shared_voices, :get_shared_voices
+      alias_method :add_voice, :add_shared_voice
+
+      private
+
+      attr_reader :client
+    end
+  end
+end

data/lib/elevenlabs_client/endpoints/audio_isolation.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class AudioIsolation
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/audio-isolation
+    # Removes background noise from audio
+    # Documentation: https://elevenlabs.io/docs/api-reference/audio-isolation
+    #
+    # @param audio_file [IO, File] The audio file from which vocals/speech will be isolated
+    # @param filename [String] Original filename for the audio file
+    # @param options [Hash] Optional parameters
+    # @option options [String] :file_format Format of input audio ('pcm_s16le_16' or 'other', defaults to 'other')
+    # @return [String] Binary audio data with background noise removed
+    def isolate(audio_file, filename, **options)
+      endpoint = "/v1/audio-isolation"
+      
+      payload = {
+        audio: @client.file_part(audio_file, filename)
+      }
+      
+      # Add optional parameters if provided
+      payload[:file_format] = options[:file_format] if options[:file_format]
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # POST /v1/audio-isolation/stream
+    # Removes background noise from audio with streaming response
+    # Documentation: https://elevenlabs.io/docs/api-reference/audio-isolation/stream
+    #
+    # @param audio_file [IO, File] The audio file from which vocals/speech will be isolated
+    # @param filename [String] Original filename for the audio file
+    # @param options [Hash] Optional parameters
+    # @option options [String] :file_format Format of input audio ('pcm_s16le_16' or 'other', defaults to 'other')
+    # @param block [Proc] Block to handle each chunk of streaming audio data
+    # @return [Faraday::Response] Response object for streaming
+    def isolate_stream(audio_file, filename, **options, &block)
+      endpoint = "/v1/audio-isolation/stream"
+      
+      payload = {
+        audio: @client.file_part(audio_file, filename)
+      }
+      
+      # Add optional parameters if provided
+      payload[:file_format] = options[:file_format] if options[:file_format]
+
+      # Use streaming multipart request
+      response = @client.instance_variable_get(:@conn).post(endpoint) do |req|
+        req.headers["xi-api-key"] = @client.api_key
+        req.body = payload
+        
+        # Set up streaming callback if block provided
+        if block_given?
+          req.options.on_data = proc do |chunk, _|
+            block.call(chunk)
+          end
+        end
+      end
+
+      @client.send(:handle_response, response)
+    end
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/audio_native.rb

@@ -0,0 +1,103 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class AudioNative
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/audio-native
+    # Creates Audio Native enabled project, optionally starts conversion and returns project ID and embeddable HTML snippet
+    # Documentation: https://elevenlabs.io/docs/api-reference/audio-native/create
+    #
+    # @param name [String] Project name
+    # @param options [Hash] Optional parameters
+    # @option options [String] :image Image URL used in the player (deprecated)
+    # @option options [String] :author Author used in the player
+    # @option options [String] :title Title used in the player
+    # @option options [Boolean] :small Whether to use small player (deprecated, defaults to false)
+    # @option options [String] :text_color Text color used in the player
+    # @option options [String] :background_color Background color used in the player
+    # @option options [Integer] :sessionization Minutes to persist session (deprecated, defaults to 0)
+    # @option options [String] :voice_id Voice ID used to voice the content
+    # @option options [String] :model_id TTS Model ID used in the player
+    # @option options [IO, File] :file Text or HTML input file containing article content
+    # @option options [String] :filename Original filename for the file
+    # @option options [Boolean] :auto_convert Whether to auto convert project to audio (defaults to false)
+    # @option options [String] :apply_text_normalization Text normalization mode ('auto', 'on', 'off', 'apply_english')
+    # @return [Hash] JSON response containing project_id, converting status, and html_snippet
+    def create(name, **options)
+      endpoint = "/v1/audio-native"
+      
+      payload = { name: name }
+      
+      # Add optional parameters if provided
+      payload[:image] = options[:image] if options[:image]
+      payload[:author] = options[:author] if options[:author]
+      payload[:title] = options[:title] if options[:title]
+      payload[:small] = options[:small] unless options[:small].nil?
+      payload[:text_color] = options[:text_color] if options[:text_color]
+      payload[:background_color] = options[:background_color] if options[:background_color]
+      payload[:sessionization] = options[:sessionization] if options[:sessionization]
+      payload[:voice_id] = options[:voice_id] if options[:voice_id]
+      payload[:model_id] = options[:model_id] if options[:model_id]
+      payload[:auto_convert] = options[:auto_convert] unless options[:auto_convert].nil?
+      payload[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
+      
+      # Add file if provided
+      if options[:file] && options[:filename]
+        payload[:file] = @client.file_part(options[:file], options[:filename])
+      end
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # POST /v1/audio-native/:project_id/content
+    # Updates content for the specific AudioNative Project
+    # Documentation: https://elevenlabs.io/docs/api-reference/audio-native/update
+    #
+    # @param project_id [String] The ID of the project to be used
+    # @param options [Hash] Optional parameters
+    # @option options [IO, File] :file Text or HTML input file containing article content
+    # @option options [String] :filename Original filename for the file
+    # @option options [Boolean] :auto_convert Whether to auto convert project to audio (defaults to false)
+    # @option options [Boolean] :auto_publish Whether to auto publish after conversion (defaults to false)
+    # @return [Hash] JSON response containing project_id, converting, publishing status, and html_snippet
+    def update_content(project_id, **options)
+      endpoint = "/v1/audio-native/#{project_id}/content"
+      
+      payload = {}
+      
+      # Add optional parameters if provided
+      payload[:auto_convert] = options[:auto_convert] unless options[:auto_convert].nil?
+      payload[:auto_publish] = options[:auto_publish] unless options[:auto_publish].nil?
+      
+      # Add file if provided
+      if options[:file] && options[:filename]
+        payload[:file] = @client.file_part(options[:file], options[:filename])
+      end
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # GET /v1/audio-native/:project_id/settings
+    # Get player settings for the specific project
+    # Documentation: https://elevenlabs.io/docs/api-reference/audio-native/settings
+    #
+    # @param project_id [String] The ID of the Studio project
+    # @return [Hash] JSON response containing enabled status, snapshot_id, and settings
+    def get_settings(project_id)
+      endpoint = "/v1/audio-native/#{project_id}/settings"
+      @client.get(endpoint)
+    end
+
+    # Alias methods for convenience
+    alias_method :create_project, :create
+    alias_method :update_project_content, :update_content
+    alias_method :project_settings, :get_settings
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/dubs.rb

@@ -8,6 +8,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing (multipart)
     # Creates a new dubbing job
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/create
     # 
     # @param file_io [IO] The audio/video file to dub
     # @param filename [String] Original filename 
@@ -19,8 +20,9 @@ module ElevenlabsClient
       payload = {
         file: @client.file_part(file_io, filename),
         mode: "automatic",
-        target_languages: target_languages,
-        name: name
+        name: name,
+        target_lang: target_languages.first,
+        num_speakers: 1
       }.compact.merge(options)
 
       @client.post_multipart("/v1/dubbing", payload)
@@ -28,6 +30,7 @@ module ElevenlabsClient
 
     # GET /v1/dubbing/{id}
     # Retrieves dubbing job details
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/get
     #
     # @param dubbing_id [String] The dubbing job ID
     # @return [Hash] Dubbing job details
@@ -37,6 +40,7 @@ module ElevenlabsClient
 
     # GET /v1/dubbing
     # Lists dubbing jobs
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing
     #
     # @param params [Hash] Query parameters (dubbing_status, page_size, etc.)
     # @return [Hash] List of dubbing jobs
@@ -46,6 +50,7 @@ module ElevenlabsClient
 
     # GET /v1/dubbing/{id}/resources
     # Retrieves dubbing resources for editing (if dubbing_studio: true was used)
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/get-resource
     #
     # @param dubbing_id [String] The dubbing job ID
     # @return [Hash] Dubbing resources
@@ -55,6 +60,7 @@ module ElevenlabsClient
 
     # DELETE /v1/dubbing/{id}
     # Deletes a dubbing project
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/delete
     #
     # @param dubbing_id [String] The dubbing job ID
     # @return [Hash] Response with status
@@ -64,6 +70,7 @@ module ElevenlabsClient
 
     # GET /v1/dubbing/resource/{dubbing_id}
     # Gets dubbing resource with detailed information including segments, speakers, etc.
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/get-resource
     #
     # @param dubbing_id [String] The dubbing job ID
     # @return [Hash] Detailed dubbing resource information
@@ -73,6 +80,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}/segment
     # Creates a new segment in dubbing resource
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/create-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param speaker_id [String] The speaker ID
@@ -94,6 +102,7 @@ module ElevenlabsClient
 
     # DELETE /v1/dubbing/resource/{dubbing_id}/segment/{segment_id}
     # Deletes a single segment from the dubbing
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/delete-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param segment_id [String] The segment ID
@@ -104,6 +113,7 @@ module ElevenlabsClient
 
     # PATCH /v1/dubbing/resource/{dubbing_id}/segment/{segment_id}/{language}
     # Updates a single segment with new text and/or start/end times
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/update-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param segment_id [String] The segment ID
@@ -124,6 +134,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing/resource/{dubbing_id}/transcribe
     # Regenerates transcriptions for specified segments
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/transcribe-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param segments [Array<String>] List of segment IDs to transcribe
@@ -135,6 +146,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing/resource/{dubbing_id}/translate
     # Regenerates translations for specified segments/languages
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/translate-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param segments [Array<String>] List of segment IDs to translate
@@ -151,6 +163,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing/resource/{dubbing_id}/dub
     # Regenerates dubs for specified segments/languages
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/dub-segment
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param segments [Array<String>] List of segment IDs to dub
@@ -167,6 +180,7 @@ module ElevenlabsClient
 
     # POST /v1/dubbing/resource/{dubbing_id}/render/{language}
     # Renders the output media for a language
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/render-project
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param language [String] The language to render
@@ -184,6 +198,7 @@ module ElevenlabsClient
 
     # PATCH /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}
     # Updates speaker metadata such as voice
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/update-speaker
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param speaker_id [String] The speaker ID
@@ -201,6 +216,7 @@ module ElevenlabsClient
 
     # GET /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}/similar-voices
     # Gets similar voices for a speaker
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/resources/get-similar-voices
     #
     # @param dubbing_id [String] The dubbing job ID
     # @param speaker_id [String] The speaker ID
@@ -209,6 +225,40 @@ module ElevenlabsClient
       @client.get("/v1/dubbing/resource/#{dubbing_id}/speaker/#{speaker_id}/similar-voices")
     end
 
+    # GET /v1/dubbing/{dubbing_id}/audio/{language_code}
+    # Returns dub as a streamed MP3 or MP4 file
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/audio/get
+    #
+    # @param dubbing_id [String] ID of the dubbing project
+    # @param language_code [String] ID of the language
+    # @return [String] Binary audio/video data
+    def get_dubbed_audio(dubbing_id, language_code)
+      endpoint = "/v1/dubbing/#{dubbing_id}/audio/#{language_code}"
+      @client.get(endpoint)
+    end
+
+    # GET /v1/dubbing/{dubbing_id}/transcript/{language_code}
+    # Returns transcript for the dub as an SRT or WEBVTT file
+    # Documentation: https://elevenlabs.io/docs/api-reference/dubbing/transcript/get-transcript-for-dub
+    #
+    # @param dubbing_id [String] ID of the dubbing project
+    # @param language_code [String] ID of the language
+    # @param options [Hash] Optional parameters
+    # @option options [String] :format_type Format to use ("srt" or "webvtt", default: "srt")
+    # @return [String] Transcript in specified format
+    def get_dubbed_transcript(dubbing_id, language_code, **options)
+      endpoint = "/v1/dubbing/#{dubbing_id}/transcript/#{language_code}"
+      
+      params = {}
+      params[:format_type] = options[:format_type] if options[:format_type]
+
+      @client.get(endpoint, params)
+    end
+
+    # Alias methods for convenience
+    alias_method :dubbed_audio, :get_dubbed_audio
+    alias_method :dubbed_transcript, :get_dubbed_transcript
+
     private
 
     attr_reader :client

data/lib/elevenlabs_client/endpoints/forced_alignment.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class ForcedAlignment
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/forced-alignment
+    # Force align an audio file to text. Get timing information for each character and word
+    # Documentation: https://elevenlabs.io/docs/api-reference/forced-alignment
+    #
+    # @param audio_file [IO, File] The audio file to align (must be less than 1GB)
+    # @param filename [String] Original filename for the audio file
+    # @param text [String] The text to align with the audio
+    # @param options [Hash] Optional parameters
+    # @option options [Boolean] :enabled_spooled_file Stream file in chunks for large files (defaults to false)
+    # @return [Hash] JSON response containing characters, words arrays with timing info, and loss score
+    def create(audio_file, filename, text, **options)
+      endpoint = "/v1/forced-alignment"
+      
+      payload = {
+        file: @client.file_part(audio_file, filename),
+        text: text
+      }
+      
+      # Add optional parameters if provided
+      payload[:enabled_spooled_file] = options[:enabled_spooled_file] unless options[:enabled_spooled_file].nil?
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # Alias methods for convenience
+    alias_method :align, :create
+    alias_method :force_align, :create
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/sound_generation.rb

@@ -36,7 +36,6 @@ module ElevenlabsClient
       @client.post_binary(full_endpoint, request_body)
     end
 
-    # Alias for backward compatibility and convenience
     alias_method :sound_generation, :generate
 
     private