elevenlabs_client 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2b65be08b17b9ae232158f2c004511a7840688e76853c014f9be37984a9639d1
-  data.tar.gz: 2de88d74e59af044cfe943e32f0d2f2d8b45f71200469a69b3f95fc7605436d2
+  metadata.gz: f1c75ecb60655822ec4d8b88e22ebae5e0a1714e5573000cd5a36c3e80bcb886
+  data.tar.gz: 5d05b4e838bc30cbc1c290b615b1c0d686ea6d6aafe9521097ddc00d0ba28189
 SHA512:
-  metadata.gz: f919ebdf7090d2f4cdd812589eccd1425e8be5e86615c04f3bf2882c7e8e8e07058db4f37cdf420e6b1948c668c3acbb177fe796b48c7f23563fa41a7204f4ce
-  data.tar.gz: 23b7dc77bb3ca90e2019d4098887b8555d103d66c1fdf259f883f7952b4c26f57671f9bd2e250e27491acc42c2518e85b37bcb48cdb678fd163f9b3be9b1d7e4
+  metadata.gz: e26733f1b2ddaaec79432e7458f2af56b50d0f29bb52bdddc4fcbdbb564c85eea40949c7304fef7a4af3da5ff2c364bb42341b3755bf385cc6e81bb429f81aa5
+  data.tar.gz: 59f527fa65e17375fa3a33eb8f7d140a3f59ccd87f51168e6f43bac5c94c3d93fa49026dc4ee6fbe5eb4fb7b0a772f6e6925b6051092f112b12936e3b154009e

data/CHANGELOG.md

@@ -5,6 +5,38 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.5.0] - 2025-09-14
+
+### Added
+
+- Text-to-Speech With Timestamps
+  - `client.text_to_speech_with_timestamps.generate(voice_id, text, **options)`
+  - Character-level `alignment` and `normalized_alignment`
+- Streaming Text-to-Speech With Timestamps
+  - `client.text_to_speech_stream_with_timestamps.stream(voice_id, text, **options, &block)`
+  - JSON streaming with audio chunks and timing per chunk
+- WebSocket Streaming Enhancements
+  - Single-context and multi-context improvements; correct query param ordering and filtering
+  - Docs: `docs/WEBSOCKET_STREAMING.md`
+- Text-to-Dialogue Streaming
+  - `client.text_to_dialogue_stream.stream(inputs, **options, &block)`
+  - Docs: `docs/TEXT_TO_DIALOGUE_STREAMING.md`
+
+### Improved
+
+- Client streaming JSON handling for timestamp streams (`post_streaming_with_timestamps`)
+- Robust parsing and block yielding across streaming tests
+- URL query parameter ordering to match expectations in tests
+
+### Tests
+
+- Added comprehensive unit and integration tests for all new endpoints
+- Full suite now: 687 examples, 0 failures
+
+### Notes
+
+- These features require valid ElevenLabs API keys and correct model/voice permissions
+
 ## [0.4.0] - 2025-09-12
 
 ### Added

data/README.md

@@ -2,7 +2,7 @@
 
 [![Gem Version](https://badge.fury.io/rb/elevenlabs_client.svg)](https://badge.fury.io/rb/elevenlabs_client)
 
-A comprehensive Ruby client library for the ElevenLabs API, supporting voice synthesis, dubbing, dialogue generation, sound effects, and AI music composition.
+A comprehensive Ruby client library for the ElevenLabs API, supporting voice synthesis, dubbing, dialogue generation, sound effects, AI music composition, voice transformation, speech transcription, audio isolation, and advanced audio processing features.
 
 ## Features
 
@@ -13,6 +13,11 @@ A comprehensive Ruby client library for the ElevenLabs API, supporting voice syn
 🎵 **Music Generation** - AI-powered music composition and streaming  
 🎨 **Voice Design** - Create custom voices from text descriptions  
 🎭 **Voice Management** - Create, edit, and manage individual voices  
+🔄 **Speech-to-Speech** - Transform audio from one voice to another (Voice Changer)  
+📝 **Speech-to-Text** - Transcribe audio and video files with advanced features  
+🔇 **Audio Isolation** - Remove background noise from audio files  
+📱 **Audio Native** - Create embeddable audio players for websites  
+⏱️ **Forced Alignment** - Get precise timing information for audio transcripts  
 🤖 **Models** - List available models and their capabilities  
 📡 **Streaming** - Real-time audio streaming  
 ⚙️ **Configurable** - Flexible configuration options  
@@ -141,6 +146,60 @@ music_data = client.music.compose(
 )
 File.open("generated_music.mp3", "wb") { |f| f.write(music_data) }
 
+# Speech-to-Speech (Voice Changer)
+File.open("input_audio.mp3", "rb") do |audio_file|
+  converted_audio = client.speech_to_speech.convert(
+    "target_voice_id", 
+    audio_file, 
+    "input_audio.mp3",
+    remove_background_noise: true
+  )
+  File.open("converted_audio.mp3", "wb") { |f| f.write(converted_audio) }
+end
+
+# Speech-to-Text Transcription
+File.open("audio.mp3", "rb") do |audio_file|
+  transcription = client.speech_to_text.create(
+    "scribe_v1",
+    file: audio_file,
+    filename: "audio.mp3",
+    diarize: true,
+    timestamps_granularity: "word"
+  )
+  puts "Transcribed: #{transcription['text']}"
+end
+
+# Audio Isolation (Background Noise Removal)
+File.open("noisy_audio.mp3", "rb") do |audio_file|
+  clean_audio = client.audio_isolation.isolate(audio_file, "noisy_audio.mp3")
+  File.open("clean_audio.mp3", "wb") { |f| f.write(clean_audio) }
+end
+
+# Audio Native (Embeddable Player)
+File.open("article.html", "rb") do |html_file|
+  project = client.audio_native.create(
+    "My Article",
+    file: html_file,
+    filename: "article.html",
+    voice_id: "voice_id",
+    auto_convert: true
+  )
+  puts "Player HTML: #{project['html_snippet']}"
+end
+
+# Forced Alignment
+File.open("speech.wav", "rb") do |audio_file|
+  alignment = client.forced_alignment.create(
+    audio_file,
+    "speech.wav",
+    "Hello world, this is a test transcript"
+  )
+  
+  alignment['words'].each do |word|
+    puts "#{word['text']}: #{word['start']}s - #{word['end']}s"
+  end
+end
+
 # Streaming Text-to-Speech
 client.text_to_speech_stream.stream("voice_id", "Streaming text") do |chunk|
   # Process audio chunk in real-time
@@ -160,6 +219,11 @@ end
 - **[Music Generation API](docs/MUSIC.md)** - AI-powered music composition and streaming
 - **[Text-to-Voice API](docs/TEXT_TO_VOICE.md)** - Design and create custom voices
 - **[Voice Management API](docs/VOICES.md)** - Manage individual voices (CRUD operations)
+- **[Speech-to-Speech API](docs/SPEECH_TO_SPEECH.md)** - Transform audio from one voice to another
+- **[Speech-to-Text API](docs/SPEECH_TO_TEXT.md)** - Transcribe audio and video files
+- **[Audio Isolation API](docs/AUDIO_ISOLATION.md)** - Remove background noise from audio
+- **[Audio Native API](docs/AUDIO_NATIVE.md)** - Create embeddable audio players
+- **[Forced Alignment API](docs/FORCED_ALIGNMENT.md)** - Get precise timing information
 - **[Models API](docs/MODELS.md)** - List available models and capabilities
 
 ### Available Endpoints
@@ -174,6 +238,11 @@ end
 | `client.music.*` | AI music composition and streaming | [MUSIC.md](docs/MUSIC.md) |
 | `client.text_to_voice.*` | Voice design and creation | [TEXT_TO_VOICE.md](docs/TEXT_TO_VOICE.md) |
 | `client.voices.*` | Voice management (CRUD) | [VOICES.md](docs/VOICES.md) |
+| `client.speech_to_speech.*` | Voice changer and audio transformation | [SPEECH_TO_SPEECH.md](docs/SPEECH_TO_SPEECH.md) |
+| `client.speech_to_text.*` | Audio/video transcription | [SPEECH_TO_TEXT.md](docs/SPEECH_TO_TEXT.md) |
+| `client.audio_isolation.*` | Background noise removal | [AUDIO_ISOLATION.md](docs/AUDIO_ISOLATION.md) |
+| `client.audio_native.*` | Embeddable audio players | [AUDIO_NATIVE.md](docs/AUDIO_NATIVE.md) |
+| `client.forced_alignment.*` | Audio-text timing alignment | [FORCED_ALIGNMENT.md](docs/FORCED_ALIGNMENT.md) |
 | `client.models.*` | Model information and capabilities | [MODELS.md](docs/MODELS.md) |
 
 ## Configuration Options
@@ -221,6 +290,9 @@ end
 - `AuthenticationError` - Invalid API key or authentication failure
 - `RateLimitError` - Rate limit exceeded
 - `ValidationError` - Invalid request parameters
+- `NotFoundError` - Resource not found (e.g., voice ID, transcript ID)
+- `BadRequestError` - Bad request with invalid parameters
+- `UnprocessableEntityError` - Request cannot be processed (e.g., invalid file format)
 - `APIError` - General API errors
 
 ## Rails Integration
@@ -235,6 +307,11 @@ The gem is designed to work seamlessly with Rails applications. See the [example
 - [MusicController](examples/music_controller.rb) - AI music composition and streaming
 - [TextToVoiceController](examples/text_to_voice_controller.rb) - Voice design and creation
 - [VoicesController](examples/voices_controller.rb) - Voice management (CRUD operations)
+- [SpeechToSpeechController](examples/speech_to_speech_controller.rb) - Voice changer and audio transformation
+- [SpeechToTextController](examples/speech_to_text_controller.rb) - Audio/video transcription with advanced features
+- [AudioIsolationController](examples/audio_isolation_controller.rb) - Background noise removal and audio cleanup
+- [AudioNativeController](examples/audio_native_controller.rb) - Embeddable audio players for websites
+- [ForcedAlignmentController](examples/forced_alignment_controller.rb) - Audio-text timing alignment and subtitle generation
 
 ## Development
 

data/lib/elevenlabs_client/client.rb

@@ -2,12 +2,13 @@
 
 require "faraday"
 require "faraday/multipart"
+require "json"
 
 module ElevenlabsClient
   class Client
     DEFAULT_BASE_URL = "https://api.elevenlabs.io"
 
-    attr_reader :base_url, :api_key, :dubs, :text_to_speech, :text_to_speech_stream, :text_to_dialogue, :sound_generation, :text_to_voice, :models, :voices, :music
+    attr_reader :base_url, :api_key, :dubs, :text_to_speech, :text_to_speech_stream, :text_to_speech_with_timestamps, :text_to_speech_stream_with_timestamps, :text_to_dialogue, :text_to_dialogue_stream, :sound_generation, :text_to_voice, :models, :voices, :music, :audio_isolation, :audio_native, :forced_alignment, :speech_to_speech, :speech_to_text, :websocket_text_to_speech
 
     def initialize(api_key: nil, base_url: nil, api_key_env: "ELEVENLABS_API_KEY", base_url_env: "ELEVENLABS_BASE_URL")
       @api_key = api_key || fetch_api_key(api_key_env)
@@ -16,12 +17,21 @@ module ElevenlabsClient
       @dubs = Dubs.new(self)
       @text_to_speech = TextToSpeech.new(self)
       @text_to_speech_stream = TextToSpeechStream.new(self)
+      @text_to_speech_with_timestamps = TextToSpeechWithTimestamps.new(self)
+      @text_to_speech_stream_with_timestamps = TextToSpeechStreamWithTimestamps.new(self)
       @text_to_dialogue = TextToDialogue.new(self)
+      @text_to_dialogue_stream = TextToDialogueStream.new(self)
       @sound_generation = SoundGeneration.new(self)
       @text_to_voice = TextToVoice.new(self)
       @models = Models.new(self)
       @voices = Voices.new(self)
       @music = Endpoints::Music.new(self)
+      @audio_isolation = AudioIsolation.new(self)
+      @audio_native = AudioNative.new(self)
+      @forced_alignment = ForcedAlignment.new(self)
+      @speech_to_speech = SpeechToSpeech.new(self)
+      @speech_to_text = SpeechToText.new(self)
+      @websocket_text_to_speech = WebSocketTextToSpeech.new(self)
     end
 
     # Makes an authenticated GET request
@@ -144,6 +154,44 @@ module ElevenlabsClient
       handle_response(response)
     end
 
+    # Makes an authenticated POST request with streaming response for timestamp data
+    # @param path [String] API endpoint path
+    # @param body [Hash, nil] Request body
+    # @param block [Proc] Block to handle each JSON chunk with timestamps
+    # @return [Faraday::Response] Response object
+    def post_streaming_with_timestamps(path, body = nil, &block)
+      buffer = ""
+      
+      response = @conn.post(path) do |req|
+        req.headers["xi-api-key"] = api_key
+        req.headers["Content-Type"] = "application/json"
+        req.body = body.to_json if body
+        
+        # Set up streaming callback for JSON chunks
+        req.options.on_data = proc do |chunk, _|
+          if block_given?
+            buffer += chunk
+            
+            # Process complete JSON objects
+            while buffer.include?("\n")
+              line, buffer = buffer.split("\n", 2)
+              next if line.strip.empty?
+              
+              begin
+                json_data = JSON.parse(line)
+                block.call(json_data)
+              rescue JSON::ParserError
+                # Skip malformed JSON lines
+                next
+              end
+            end
+          end
+        end
+      end
+
+      handle_response(response)
+    end
+
     # Helper method to create Faraday::Multipart::FilePart
     # @param file_io [IO] File IO object
     # @param filename [String] Original filename

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