elevenlabs_client 0.5.0 → 0.6.0

data/lib/elevenlabs_client/endpoints/speech_to_text.rb

@@ -96,10 +96,23 @@ module ElevenlabsClient
       @client.get(endpoint)
     end
 
+    # DELETE /v1/speech-to-text/transcripts/:transcription_id
+    # Delete a previously generated transcript by its ID
+    # Documentation: https://elevenlabs.io/docs/api-reference/speech-to-text/delete-transcript
+    #
+    # @param transcription_id [String] The unique ID of the transcript to delete
+    # @return [Hash] Delete confirmation response
+    def delete_transcript(transcription_id)
+      endpoint = "/v1/speech-to-text/transcripts/#{transcription_id}"
+      @client.delete(endpoint)
+    end
+
     # Alias methods for convenience
     alias_method :transcribe, :create
     alias_method :get_transcription, :get_transcript
     alias_method :retrieve_transcript, :get_transcript
+    alias_method :delete_transcription, :delete_transcript
+    alias_method :remove_transcript, :delete_transcript
 
     private
 

data/lib/elevenlabs_client/endpoints/text_to_dialogue.rb

@@ -30,7 +30,40 @@ module ElevenlabsClient
       @client.post_binary(endpoint, request_body)
     end
 
-    # Alias for backward compatibility and convenience
+    # POST /v1/text-to-dialogue/stream
+    # Converts a list of text and voice ID pairs into speech (dialogue) and returns an audio stream.
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-dialogue/stream
+    #
+    # @param inputs [Array<Hash>] A list of dialogue inputs, each containing text and a voice ID
+    # @param options [Hash] Optional parameters
+    # @option options [String] :model_id Identifier of the model to be used (default: "eleven_v3")
+    # @option options [String] :language_code ISO 639-1 language code
+    # @option options [Hash] :settings Settings controlling the dialogue generation
+    # @option options [Array<Hash>] :pronunciation_dictionary_locators Pronunciation dictionary locators (max 3)
+    # @option options [Integer] :seed Deterministic sampling seed (0-4294967295)
+    # @option options [String] :apply_text_normalization Text normalization mode ("auto", "on", "off")
+    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
+    # @param block [Proc] Block to handle each audio chunk
+    # @return [Faraday::Response] The response object
+    def stream(inputs, **options, &block)
+      # Build endpoint with optional query params
+      output_format = options[:output_format] || "mp3_44100_128"
+      endpoint = "/v1/text-to-dialogue/stream?output_format=#{output_format}"
+
+      # Build request body
+      request_body = { inputs: inputs }
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:language_code] = options[:language_code] if options[:language_code]
+      request_body[:settings] = options[:settings] if options[:settings]
+      request_body[:pronunciation_dictionary_locators] = options[:pronunciation_dictionary_locators] if options[:pronunciation_dictionary_locators]
+      request_body[:seed] = options[:seed] if options[:seed]
+      request_body[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
+
+      @client.post_streaming(endpoint, request_body, &block)
+    end
+
+    # Alias for convenience
+    alias_method :text_to_dialogue_stream, :stream
     alias_method :text_to_dialogue, :convert
 
     private

data/lib/elevenlabs_client/endpoints/text_to_speech.rb

@@ -33,7 +33,153 @@ module ElevenlabsClient
       end
     end
 
-    # Alias for backward compatibility and convenience
+    # POST /v1/text-to-speech/{voice_id}/with-timestamps
+    # Generate speech from text with precise character-level timing information
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/with-timestamps
+    #
+    # @param voice_id [String] Voice ID to be used
+    # @param text [String] The text that will get converted into speech
+    # @param options [Hash] Optional TTS parameters
+    # @option options [String] :model_id Model identifier (defaults to "eleven_multilingual_v2")
+    # @option options [String] :language_code ISO 639-1 language code for text normalization
+    # @option options [Hash] :voice_settings Voice settings overriding stored settings
+    # @option options [Array<Hash>] :pronunciation_dictionary_locators Pronunciation dictionary locators (max 3)
+    # @option options [Integer] :seed Deterministic sampling seed (0-4294967295)
+    # @option options [String] :previous_text Text that came before current request
+    # @option options [String] :next_text Text that comes after current request
+    # @option options [Array<String>] :previous_request_ids Request IDs of previous samples (max 3)
+    # @option options [Array<String>] :next_request_ids Request IDs of next samples (max 3)
+    # @option options [String] :apply_text_normalization Text normalization mode ("auto", "on", "off")
+    # @option options [Boolean] :apply_language_text_normalization Language text normalization
+    # @option options [Boolean] :use_pvc_as_ivc Use IVC version instead of PVC (deprecated)
+    # @option options [Boolean] :enable_logging Enable logging (defaults to true)
+    # @option options [Integer] :optimize_streaming_latency Latency optimizations (0-4, deprecated)
+    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
+    # @return [Hash] Response containing audio_base64, alignment, and normalized_alignment
+    def convert_with_timestamps(voice_id, text, **options)
+      # Build query parameters
+      query_params = {}
+      query_params[:enable_logging] = options[:enable_logging] unless options[:enable_logging].nil?
+      query_params[:optimize_streaming_latency] = options[:optimize_streaming_latency] if options[:optimize_streaming_latency]
+      query_params[:output_format] = options[:output_format] if options[:output_format]
+      
+      # Build endpoint with query parameters
+      endpoint = "/v1/text-to-speech/#{voice_id}/with-timestamps"
+      if query_params.any?
+        query_string = query_params.map { |k, v| "#{k}=#{v}" }.join("&")
+        endpoint += "?#{query_string}"
+      end
+      
+      # Build request body
+      request_body = { text: text }
+      
+      # Add optional body parameters
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:language_code] = options[:language_code] if options[:language_code]
+      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
+      request_body[:pronunciation_dictionary_locators] = options[:pronunciation_dictionary_locators] if options[:pronunciation_dictionary_locators]
+      request_body[:seed] = options[:seed] if options[:seed]
+      request_body[:previous_text] = options[:previous_text] if options[:previous_text]
+      request_body[:next_text] = options[:next_text] if options[:next_text]
+      request_body[:previous_request_ids] = options[:previous_request_ids] if options[:previous_request_ids]
+      request_body[:next_request_ids] = options[:next_request_ids] if options[:next_request_ids]
+      request_body[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
+      request_body[:apply_language_text_normalization] = options[:apply_language_text_normalization] unless options[:apply_language_text_normalization].nil?
+      request_body[:use_pvc_as_ivc] = options[:use_pvc_as_ivc] unless options[:use_pvc_as_ivc].nil?
+
+      @client.post(endpoint, request_body)
+    end
+
+    alias_method :text_to_speech_with_timestamps, :convert_with_timestamps
+
+    # POST /v1/text-to-speech/{voice_id}/stream
+    # Stream text-to-speech audio in real-time chunks
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/stream
+    #
+    # @param voice_id [String] The ID of the voice to use
+    # @param text [String] Text to synthesize
+    # @param options [Hash] Optional TTS parameters
+    # @option options [String] :model_id Model to use (defaults to "eleven_multilingual_v2")
+    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
+    # @option options [Hash] :voice_settings Voice configuration
+    # @param block [Proc] Block to handle each audio chunk
+    # @return [Faraday::Response] The response object
+    def stream(voice_id, text, **options, &block)
+      output_format = options[:output_format] || "mp3_44100_128"
+      endpoint = "/v1/text-to-speech/#{voice_id}/stream?output_format=#{output_format}"
+      
+      request_body = {
+        text: text,
+        model_id: options[:model_id] || "eleven_multilingual_v2"
+      }
+      
+      # Add voice_settings if provided
+      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
+
+      @client.post_streaming(endpoint, request_body, &block)
+    end
+
+    # POST /v1/text-to-speech/{voice_id}/stream/with-timestamps
+    # Stream text-to-speech audio with character-level timing information
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps
+    #
+    # @param voice_id [String] Voice ID to be used
+    # @param text [String] The text that will get converted into speech
+    # @param options [Hash] Optional TTS parameters
+    # @option options [String] :model_id Model identifier (defaults to "eleven_multilingual_v2")
+    # @option options [String] :language_code ISO 639-1 language code for text normalization
+    # @option options [Hash] :voice_settings Voice settings overriding stored settings
+    # @option options [Array<Hash>] :pronunciation_dictionary_locators Pronunciation dictionary locators (max 3)
+    # @option options [Integer] :seed Deterministic sampling seed (0-4294967295)
+    # @option options [String] :previous_text Text that came before current request
+    # @option options [String] :next_text Text that comes after current request
+    # @option options [Array<String>] :previous_request_ids Request IDs of previous samples (max 3)
+    # @option options [Array<String>] :next_request_ids Request IDs of next samples (max 3)
+    # @option options [String] :apply_text_normalization Text normalization mode ("auto", "on", "off")
+    # @option options [Boolean] :apply_language_text_normalization Language text normalization
+    # @option options [Boolean] :use_pvc_as_ivc Use IVC version instead of PVC (deprecated)
+    # @option options [Boolean] :enable_logging Enable logging (defaults to true)
+    # @option options [Integer] :optimize_streaming_latency Latency optimizations (0-4, deprecated)
+    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
+    # @param block [Proc] Block to handle each streaming chunk containing audio and timing data
+    # @return [Faraday::Response] The response object
+    def stream_with_timestamps(voice_id, text, **options, &block)
+      # Build query parameters
+      query_params = {}
+      query_params[:enable_logging] = options[:enable_logging] unless options[:enable_logging].nil?
+      query_params[:optimize_streaming_latency] = options[:optimize_streaming_latency] if options[:optimize_streaming_latency]
+      query_params[:output_format] = options[:output_format] if options[:output_format]
+      
+      # Build endpoint with query parameters
+      endpoint = "/v1/text-to-speech/#{voice_id}/stream/with-timestamps"
+      if query_params.any?
+        query_string = query_params.map { |k, v| "#{k}=#{v}" }.join("&")
+        endpoint += "?#{query_string}"
+      end
+      
+      # Build request body
+      request_body = { text: text }
+      
+      # Add optional body parameters
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:language_code] = options[:language_code] if options[:language_code]
+      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
+      request_body[:pronunciation_dictionary_locators] = options[:pronunciation_dictionary_locators] if options[:pronunciation_dictionary_locators]
+      request_body[:seed] = options[:seed] if options[:seed]
+      request_body[:previous_text] = options[:previous_text] if options[:previous_text]
+      request_body[:next_text] = options[:next_text] if options[:next_text]
+      request_body[:previous_request_ids] = options[:previous_request_ids] if options[:previous_request_ids]
+      request_body[:next_request_ids] = options[:next_request_ids] if options[:next_request_ids]
+      request_body[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
+      request_body[:apply_language_text_normalization] = options[:apply_language_text_normalization] unless options[:apply_language_text_normalization].nil?
+      request_body[:use_pvc_as_ivc] = options[:use_pvc_as_ivc] unless options[:use_pvc_as_ivc].nil?
+
+      # Use streaming method with JSON parsing for timestamp data
+      @client.post_streaming_with_timestamps(endpoint, request_body, &block)
+    end
+
+    alias_method :text_to_speech_stream_with_timestamps, :stream_with_timestamps
+    alias_method :text_to_speech_stream, :stream
     alias_method :text_to_speech, :convert
 
     private

data/lib/elevenlabs_client/endpoints/text_to_voice.rb

@@ -74,6 +74,18 @@ module ElevenlabsClient
       @client.post(endpoint, request_body)
     end
 
+    # GET /v1/text-to-voice/:generated_voice_id/stream
+    # Stream a voice preview that was created via the /v1/text-to-voice/design endpoint
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-voice/stream-voice-preview
+    #
+    # @param generated_voice_id [String] The generated_voice_id to stream
+    # @param block [Proc] Block to handle each streaming chunk
+    # @return [Faraday::Response] The response object
+    def stream_preview(generated_voice_id, &block)
+      endpoint = "/v1/text-to-voice/#{generated_voice_id}/stream"
+      @client.get_streaming(endpoint, &block)
+    end
+
     # GET /v1/voices
     # Retrieves all voices associated with your Elevenlabs account
     # Documentation: https://elevenlabs.io/docs/api-reference/voices
@@ -84,9 +96,9 @@ module ElevenlabsClient
       @client.get(endpoint)
     end
 
-    # Alias methods for backward compatibility and convenience
     alias_method :design_voice, :design
     alias_method :create_from_generated_voice, :create
+    alias_method :stream_voice_preview, :stream_preview
 
     private
 

data/lib/elevenlabs_client/endpoints/voices.rb

@@ -110,29 +110,6 @@ module ElevenlabsClient
       @client.delete(endpoint)
     end
 
-    # Check if a voice is banned (safety control)
-    # @param voice_id [String] The ID of the voice to check
-    # @return [Boolean] True if the voice is banned
-    def banned?(voice_id)
-      voice = get(voice_id)
-      voice["safety_control"] == "BAN"
-    rescue ElevenlabsClient::ValidationError, ElevenlabsClient::APIError, ElevenlabsClient::NotFoundError
-      # If we can't get the voice, assume it's not banned
-      false
-    end
-
-    # Check if a voice is active (exists in the voice list)
-    # @param voice_id [String] The ID of the voice to check
-    # @return [Boolean] True if the voice is active
-    def active?(voice_id)
-      voices = list
-      active_voice_ids = voices["voices"].map { |voice| voice["voice_id"] }
-      active_voice_ids.include?(voice_id)
-    rescue ElevenlabsClient::ValidationError, ElevenlabsClient::APIError, ElevenlabsClient::NotFoundError
-      # If we can't get the voice list, assume it's not active
-      false
-    end
-
     # POST /v1/similar-voices
     # Returns a list of shared voices similar to the provided audio sample
     # Documentation: https://elevenlabs.io/docs/api-reference/voices/similar-voices
@@ -491,7 +468,6 @@ module ElevenlabsClient
       @client.post_multipart(endpoint, payload)
     end
 
-    # Alias methods for backward compatibility and convenience
     alias_method :get_voice, :get
     alias_method :list_voices, :list
     alias_method :create_voice, :create
@@ -502,6 +478,29 @@ module ElevenlabsClient
     alias_method :voice_settings, :get_settings
     alias_method :update_settings, :edit_settings
 
+    # Check if a voice is banned (safety control)
+    # @param voice_id [String] The ID of the voice to check
+    # @return [Boolean] True if the voice is banned
+    def banned?(voice_id)
+      voice = get(voice_id)
+      voice["safety_control"] == "BAN"
+    rescue ElevenlabsClient::ValidationError, ElevenlabsClient::APIError, ElevenlabsClient::NotFoundError
+      # If we can't get the voice, assume it's not banned
+      false
+    end
+
+    # Check if a voice is active (exists in the voice list)
+    # @param voice_id [String] The ID of the voice to check
+    # @return [Boolean] True if the voice is active
+    def active?(voice_id)
+      voices = list
+      active_voice_ids = voices["voices"].map { |voice| voice["voice_id"] }
+      active_voice_ids.include?(voice_id)
+    rescue ElevenlabsClient::ValidationError, ElevenlabsClient::APIError, ElevenlabsClient::NotFoundError
+      # If we can't get the voice list, assume it's not active
+      false
+    end
+
     private
 
     attr_reader :client

data/lib/elevenlabs_client/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ElevenlabsClient
-  VERSION = "0.5.0"
+  VERSION = "0.6.0"
 end

data/lib/elevenlabs_client.rb

@@ -5,14 +5,14 @@ require_relative "elevenlabs_client/errors"
 require_relative "elevenlabs_client/settings"
 require_relative "elevenlabs_client/endpoints/dubs"
 require_relative "elevenlabs_client/endpoints/text_to_speech"
-require_relative "elevenlabs_client/endpoints/text_to_speech_stream"
-require_relative "elevenlabs_client/endpoints/text_to_speech_with_timestamps"
-require_relative "elevenlabs_client/endpoints/text_to_speech_stream_with_timestamps"
 require_relative "elevenlabs_client/endpoints/text_to_dialogue"
-require_relative "elevenlabs_client/endpoints/text_to_dialogue_stream"
 require_relative "elevenlabs_client/endpoints/sound_generation"
 require_relative "elevenlabs_client/endpoints/text_to_voice"
-require_relative "elevenlabs_client/endpoints/models"
+require_relative "elevenlabs_client/endpoints/admin/models"
+require_relative "elevenlabs_client/endpoints/admin/history"
+require_relative "elevenlabs_client/endpoints/admin/usage"
+require_relative "elevenlabs_client/endpoints/admin/user"
+require_relative "elevenlabs_client/endpoints/admin/voice_library"
 require_relative "elevenlabs_client/endpoints/voices"
 require_relative "elevenlabs_client/endpoints/music"
 require_relative "elevenlabs_client/endpoints/audio_isolation"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: elevenlabs_client
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Vitor Oliveira
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-09-14 00:00:00.000000000 Z
+date: 2025-09-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday
@@ -122,6 +122,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: bundler-audit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
 description: A Ruby client library for interacting with ElevenLabs dubbing and voice
   synthesis APIs
 email:
@@ -135,21 +149,21 @@ files:
 - README.md
 - lib/elevenlabs_client.rb
 - lib/elevenlabs_client/client.rb
+- lib/elevenlabs_client/endpoints/admin/history.rb
+- lib/elevenlabs_client/endpoints/admin/models.rb
+- lib/elevenlabs_client/endpoints/admin/usage.rb
+- lib/elevenlabs_client/endpoints/admin/user.rb
+- lib/elevenlabs_client/endpoints/admin/voice_library.rb
 - lib/elevenlabs_client/endpoints/audio_isolation.rb
 - lib/elevenlabs_client/endpoints/audio_native.rb
 - lib/elevenlabs_client/endpoints/dubs.rb
 - lib/elevenlabs_client/endpoints/forced_alignment.rb
-- lib/elevenlabs_client/endpoints/models.rb
 - lib/elevenlabs_client/endpoints/music.rb
 - lib/elevenlabs_client/endpoints/sound_generation.rb
 - lib/elevenlabs_client/endpoints/speech_to_speech.rb
 - lib/elevenlabs_client/endpoints/speech_to_text.rb
 - lib/elevenlabs_client/endpoints/text_to_dialogue.rb
-- lib/elevenlabs_client/endpoints/text_to_dialogue_stream.rb
 - lib/elevenlabs_client/endpoints/text_to_speech.rb
-- lib/elevenlabs_client/endpoints/text_to_speech_stream.rb
-- lib/elevenlabs_client/endpoints/text_to_speech_stream_with_timestamps.rb
-- lib/elevenlabs_client/endpoints/text_to_speech_with_timestamps.rb
 - lib/elevenlabs_client/endpoints/text_to_voice.rb
 - lib/elevenlabs_client/endpoints/voices.rb
 - lib/elevenlabs_client/endpoints/websocket_text_to_speech.rb

data/lib/elevenlabs_client/endpoints/models.rb

@@ -1,26 +0,0 @@
-# frozen_string_literal: true
-
-module ElevenlabsClient
-  class Models
-    def initialize(client)
-      @client = client
-    end
-
-    # GET /v1/models
-    # Gets a list of available models
-    # Documentation: https://elevenlabs.io/docs/api-reference/models/list
-    #
-    # @return [Hash] The JSON response containing an array of models
-    def list
-      endpoint = "/v1/models"
-      @client.get(endpoint)
-    end
-
-    # Alias for backward compatibility and convenience
-    alias_method :list_models, :list
-
-    private
-
-    attr_reader :client
-  end
-end

data/lib/elevenlabs_client/endpoints/text_to_dialogue_stream.rb

@@ -1,50 +0,0 @@
-# frozen_string_literal: true
-
-module ElevenlabsClient
-  class TextToDialogueStream
-    def initialize(client)
-      @client = client
-    end
-
-    # POST /v1/text-to-dialogue/stream
-    # Converts a list of text and voice ID pairs into speech (dialogue) and returns an audio stream.
-    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-dialogue/stream
-    #
-    # @param inputs [Array<Hash>] A list of dialogue inputs, each containing text and a voice ID
-    # @param options [Hash] Optional parameters
-    # @option options [String] :model_id Identifier of the model to be used (default: "eleven_v3")
-    # @option options [String] :language_code ISO 639-1 language code
-    # @option options [Hash] :settings Settings controlling the dialogue generation
-    # @option options [Array<Hash>] :pronunciation_dictionary_locators Pronunciation dictionary locators (max 3)
-    # @option options [Integer] :seed Deterministic sampling seed (0-4294967295)
-    # @option options [String] :apply_text_normalization Text normalization mode ("auto", "on", "off")
-    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
-    # @param block [Proc] Block to handle each audio chunk
-    # @return [Faraday::Response] The response object
-    def stream(inputs, **options, &block)
-      # Build endpoint with optional query params
-      output_format = options[:output_format] || "mp3_44100_128"
-      endpoint = "/v1/text-to-dialogue/stream?output_format=#{output_format}"
-
-      # Build request body
-      request_body = { inputs: inputs }
-      request_body[:model_id] = options[:model_id] if options[:model_id]
-      request_body[:language_code] = options[:language_code] if options[:language_code]
-      request_body[:settings] = options[:settings] if options[:settings]
-      request_body[:pronunciation_dictionary_locators] = options[:pronunciation_dictionary_locators] if options[:pronunciation_dictionary_locators]
-      request_body[:seed] = options[:seed] if options[:seed]
-      request_body[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
-
-      @client.post_streaming(endpoint, request_body, &block)
-    end
-
-    # Alias for convenience
-    alias_method :text_to_dialogue_stream, :stream
-
-    private
-
-    attr_reader :client
-  end
-end
-
-

data/lib/elevenlabs_client/endpoints/text_to_speech_stream.rb

@@ -1,43 +0,0 @@
-# frozen_string_literal: true
-
-module ElevenlabsClient
-  class TextToSpeechStream
-    def initialize(client)
-      @client = client
-    end
-
-    # POST /v1/text-to-speech/{voice_id}/stream
-    # Stream text-to-speech audio in real-time chunks
-    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/stream
-    #
-    # @param voice_id [String] The ID of the voice to use
-    # @param text [String] Text to synthesize
-    # @param options [Hash] Optional TTS parameters
-    # @option options [String] :model_id Model to use (defaults to "eleven_multilingual_v2")
-    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
-    # @option options [Hash] :voice_settings Voice configuration
-    # @param block [Proc] Block to handle each audio chunk
-    # @return [Faraday::Response] The response object
-    def stream(voice_id, text, **options, &block)
-      output_format = options[:output_format] || "mp3_44100_128"
-      endpoint = "/v1/text-to-speech/#{voice_id}/stream?output_format=#{output_format}"
-      
-      request_body = {
-        text: text,
-        model_id: options[:model_id] || "eleven_multilingual_v2"
-      }
-      
-      # Add voice_settings if provided
-      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
-
-      @client.post_streaming(endpoint, request_body, &block)
-    end
-
-    # Alias for backward compatibility
-    alias_method :text_to_speech_stream, :stream
-
-    private
-
-    attr_reader :client
-  end
-end

data/lib/elevenlabs_client/endpoints/text_to_speech_stream_with_timestamps.rb

@@ -1,75 +0,0 @@
-# frozen_string_literal: true
-
-module ElevenlabsClient
-  class TextToSpeechStreamWithTimestamps
-    def initialize(client)
-      @client = client
-    end
-
-    # POST /v1/text-to-speech/{voice_id}/stream/with-timestamps
-    # Stream text-to-speech audio with character-level timing information
-    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps
-    #
-    # @param voice_id [String] Voice ID to be used
-    # @param text [String] The text that will get converted into speech
-    # @param options [Hash] Optional TTS parameters
-    # @option options [String] :model_id Model identifier (defaults to "eleven_multilingual_v2")
-    # @option options [String] :language_code ISO 639-1 language code for text normalization
-    # @option options [Hash] :voice_settings Voice settings overriding stored settings
-    # @option options [Array<Hash>] :pronunciation_dictionary_locators Pronunciation dictionary locators (max 3)
-    # @option options [Integer] :seed Deterministic sampling seed (0-4294967295)
-    # @option options [String] :previous_text Text that came before current request
-    # @option options [String] :next_text Text that comes after current request
-    # @option options [Array<String>] :previous_request_ids Request IDs of previous samples (max 3)
-    # @option options [Array<String>] :next_request_ids Request IDs of next samples (max 3)
-    # @option options [String] :apply_text_normalization Text normalization mode ("auto", "on", "off")
-    # @option options [Boolean] :apply_language_text_normalization Language text normalization
-    # @option options [Boolean] :use_pvc_as_ivc Use IVC version instead of PVC (deprecated)
-    # @option options [Boolean] :enable_logging Enable logging (defaults to true)
-    # @option options [Integer] :optimize_streaming_latency Latency optimizations (0-4, deprecated)
-    # @option options [String] :output_format Output format (defaults to "mp3_44100_128")
-    # @param block [Proc] Block to handle each streaming chunk containing audio and timing data
-    # @return [Faraday::Response] The response object
-    def stream(voice_id, text, **options, &block)
-      # Build query parameters
-      query_params = {}
-      query_params[:enable_logging] = options[:enable_logging] unless options[:enable_logging].nil?
-      query_params[:optimize_streaming_latency] = options[:optimize_streaming_latency] if options[:optimize_streaming_latency]
-      query_params[:output_format] = options[:output_format] if options[:output_format]
-      
-      # Build endpoint with query parameters
-      endpoint = "/v1/text-to-speech/#{voice_id}/stream/with-timestamps"
-      if query_params.any?
-        query_string = query_params.map { |k, v| "#{k}=#{v}" }.join("&")
-        endpoint += "?#{query_string}"
-      end
-      
-      # Build request body
-      request_body = { text: text }
-      
-      # Add optional body parameters
-      request_body[:model_id] = options[:model_id] if options[:model_id]
-      request_body[:language_code] = options[:language_code] if options[:language_code]
-      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
-      request_body[:pronunciation_dictionary_locators] = options[:pronunciation_dictionary_locators] if options[:pronunciation_dictionary_locators]
-      request_body[:seed] = options[:seed] if options[:seed]
-      request_body[:previous_text] = options[:previous_text] if options[:previous_text]
-      request_body[:next_text] = options[:next_text] if options[:next_text]
-      request_body[:previous_request_ids] = options[:previous_request_ids] if options[:previous_request_ids]
-      request_body[:next_request_ids] = options[:next_request_ids] if options[:next_request_ids]
-      request_body[:apply_text_normalization] = options[:apply_text_normalization] if options[:apply_text_normalization]
-      request_body[:apply_language_text_normalization] = options[:apply_language_text_normalization] unless options[:apply_language_text_normalization].nil?
-      request_body[:use_pvc_as_ivc] = options[:use_pvc_as_ivc] unless options[:use_pvc_as_ivc].nil?
-
-      # Use streaming method with JSON parsing for timestamp data
-      @client.post_streaming_with_timestamps(endpoint, request_body, &block)
-    end
-
-    # Alias for backward compatibility
-    alias_method :text_to_speech_stream_with_timestamps, :stream
-
-    private
-
-    attr_reader :client
-  end
-end