elevenlabs_client 0.2.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2eb4466ffb626d55734bcd3569141c50293bbee7219fcffc252bd161f3bacac5
-  data.tar.gz: 2b045b85c15865d17f000a924c2f5088558d81f85b50e1273a11b6950e4eda9f
+  metadata.gz: 2b65be08b17b9ae232158f2c004511a7840688e76853c014f9be37984a9639d1
+  data.tar.gz: 2de88d74e59af044cfe943e32f0d2f2d8b45f71200469a69b3f95fc7605436d2
 SHA512:
-  metadata.gz: 30cfe941d5a311175436c55e5952d743efaa42410fc38e3e2c6df5c1b8db374720d960f86cc57c8985127028b6bc9312a360d4744e7536913576a1ce4c3bbb9e
-  data.tar.gz: ec656950468c78eede815ae879c1e7475e6c8d64d725a850c4d6ebf95f7ce9c058174b734a4cec19c4c65133ede31aac0b57f08b271e17ce6a87904c2609e3e3
+  metadata.gz: f919ebdf7090d2f4cdd812589eccd1425e8be5e86615c04f3bf2882c7e8e8e07058db4f37cdf420e6b1948c668c3acbb177fe796b48c7f23563fa41a7204f4ce
+  data.tar.gz: 23b7dc77bb3ca90e2019d4098887b8555d103d66c1fdf259f883f7952b4c26f57671f9bd2e250e27491acc42c2518e85b37bcb48cdb678fd163f9b3be9b1d7e4

data/CHANGELOG.md

@@ -5,7 +5,174 @@ 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).
 
-## [Unreleased]
+## [0.4.0] - 2025-09-12
+
+### Added
+
+- **🎵 Dubbing Generation API** 
+  - `delete(dubbing_id)` - Delete dubbing projects
+  - `get_resource(dubbing_id)` - Get detailed resource information
+  - `create_segment(options)` - Create new segments
+  - `delete_segment(options)` - Delete segments
+  - `update_segment(options)` - Update segment text/timing
+  - `transcribe_segment(options)` - Regenerate transcriptions
+  - `translate_segment(options)` - Regenerate translations
+  - `dub_segment(options)` - Regenerate dubs
+  - `render_project(options)` - Render output media
+  - `update_speaker(options)` - Update speaker voices
+  - `get_similar_voices(options)` - Get voice recommendations
+- **🔧 HTTP Client Improvements** - Added HTTP method
+  - Added `patch` method for PATCH requests
+
+## [0.3.0] - 2025-09-12
+
+### Added
+- **🎵 Music Generation API** - AI-powered music composition and streaming
+  - `client.music.compose(options)` - Generate music from text prompts
+  - `client.music.compose_stream(options, &block)` - Real-time music streaming
+  - `client.music.compose_detailed(options)` - Generate music with metadata
+  - `client.music.create_plan(options)` - Create structured composition plans
+- **🎭 Voice Management API** - Complete CRUD operations for individual voices
+  - `client.voices.get(voice_id)` - Get detailed voice information
+  - `client.voices.list()` - List all voices in account
+  - `client.voices.create(name, samples, **options)` - Create custom voices from audio samples
+  - `client.voices.edit(voice_id, samples, **options)` - Edit existing voices
+  - `client.voices.delete(voice_id)` - Delete voices from account
+  - `client.voices.banned?(voice_id)` - Check voice safety status
+  - `client.voices.active?(voice_id)` - Check voice availability
+- **📋 Enhanced Rakefile** - Comprehensive gem management and development tasks
+  - Build, install, push, and clean gem operations
+  - Development tools (linting, testing, security audit)
+  - Documentation generation and serving
+  - Release preparation and management
+  - Maintenance and cleanup tasks
+
+### Enhanced
+- **🚨 Consolidated Error Handling** - Unified error handling across all endpoints
+  - Merged `handle_response`, `handle_binary_response`, and `handle_streaming_response` into single method
+  - Enhanced error message extraction from JSON, nested objects, arrays, and plain text
+  - More specific error types: `BadRequestError`, `NotFoundError`, `UnprocessableEntityError`
+  - Better error messages extracted from actual API responses instead of generic fallbacks
+- **🔧 HTTP Client Improvements** - Added missing HTTP methods and consolidated functionality
+  - Added `delete` method for DELETE requests
+  - Enhanced `post_with_custom_headers` for flexible header management
+  - Consistent error handling across all HTTP methods (GET, POST, DELETE, multipart, binary, streaming)
+- **📚 Documentation Organization** - Comprehensive documentation for all new features
+  - [MUSIC.md](docs/MUSIC.md) - Complete music generation guide (570 lines)
+  - [VOICES.md](docs/VOICES.md) - Voice management documentation (519 lines)
+  - Enhanced README with music capabilities and updated feature list
+  - Professional Rails integration examples
+
+### New Error Classes
+- `ElevenlabsClient::BadRequestError` (400) - Invalid parameters or malformed requests
+- `ElevenlabsClient::NotFoundError` (404) - Resource not found
+- `ElevenlabsClient::UnprocessableEntityError` (422) - Valid request but invalid data
+
+### Music Generation Features
+- **🎼 Composition Styles** - Support for all major music genres
+  - Electronic: EDM, House, Techno, Ambient, Synthwave
+  - Orchestral: Classical, Film Score, Epic Orchestral
+  - Popular: Pop, Rock, Hip-Hop, Country, Folk
+  - Jazz & Blues: Traditional Jazz, Smooth Jazz, Blues
+  - World Music: Celtic, Medieval, New Age, Ethnic
+- **🎛️ Advanced Controls** - Detailed composition parameters
+  - Custom composition plans with sections, tempo, key, instruments
+  - Multiple output formats (MP3, WAV) with quality settings
+  - Music length control (5 seconds to 5 minutes)
+  - Model selection for different generation approaches
+- **📡 Streaming Support** - Real-time music generation and playback
+  - Chunk-based streaming for immediate playback
+  - Memory-efficient processing for long compositions
+  - WebSocket integration for live applications
+
+### Voice Management Features
+- **🎤 Voice Creation** - Create custom voices from audio samples
+  - Multiple sample upload support for better quality
+  - Voice metadata and labeling system
+  - Quality validation and optimization
+- **🔧 Voice Editing** - Modify existing voices
+  - Add new samples to improve voice quality
+  - Update voice metadata and descriptions
+  - Batch voice operations
+- **🔍 Voice Discovery** - Advanced voice management
+  - Search and filter voices by category, labels, quality
+  - Voice status checking (active, banned, available)
+  - Voice analytics and usage tracking
+
+### Rails Integration Examples
+- **[MusicController](examples/music_controller.rb)** - Complete music generation implementation
+  - Basic and advanced music generation endpoints
+  - Streaming music with real-time playback
+  - Composition planning and structured music creation
+  - Batch generation and music library management
+  - Interactive music generation with user preferences
+- **[VoicesController](examples/voices_controller.rb)** - Voice management implementation
+  - Full CRUD operations for voice management
+  - File upload handling for voice samples
+  - Voice search and filtering capabilities
+  - Batch voice operations and management workflows
+
+### Technical Improvements
+- **🧪 Comprehensive Testing** - Expanded test coverage
+  - **57 new music tests** (24 unit + 33 integration)
+  - **Enhanced error handling tests** across all endpoints
+  - **Total test coverage**: 300+ tests with consistent passing
+- **🏗️ Architecture Consolidation** - Cleaner codebase
+  - Removed duplicate error handling methods
+  - Consolidated HTTP response processing
+  - Enhanced error message extraction with fallback handling
+  - Improved code organization and maintainability
+- **📦 Release Management** - Professional release workflow
+  - Automated release preparation tasks
+  - Version management and changelog automation
+  - Security auditing and dependency management
+  - Documentation generation and validation
+
+### Breaking Changes
+- **Error Handling** - More specific error types may require catch block updates
+  ```ruby
+  # Before (v0.2.0)
+  rescue ElevenlabsClient::ValidationError => e
+    # Handle all 4xx errors
+  end
+  
+  # After (v0.3.0) - More specific handling
+  rescue ElevenlabsClient::BadRequestError => e
+    # Handle 400 Bad Request
+  rescue ElevenlabsClient::NotFoundError => e
+    # Handle 404 Not Found
+  rescue ElevenlabsClient::UnprocessableEntityError => e
+    # Handle 422 Unprocessable Entity
+  rescue ElevenlabsClient::ValidationError => e
+    # Handle other 4xx errors
+  end
+  ```
+
+### Migration Guide
+```ruby
+# New Music API Usage
+client = ElevenlabsClient.new
+
+# Generate music
+music_data = client.music.compose(
+  prompt: "Upbeat electronic dance track",
+  music_length_ms: 30000
+)
+
+# Stream music generation
+client.music.compose_stream(prompt: "Relaxing ambient") do |chunk|
+  # Process audio chunk in real-time
+end
+
+# Voice management
+voices = client.voices.list
+voice = client.voices.get("voice_id")
+
+# Create custom voice
+File.open("sample.mp3", "rb") do |sample|
+  voice = client.voices.create("My Voice", [sample])
+end
+```
 
 ## [0.2.0] - 2025-09-12
 
@@ -104,4 +271,4 @@ client.dubs.create(file_io: file, filename: "video.mp4", target_languages: ["es"
 - **File Support**: Multiple video and audio formats (MP4, MOV, MP3, WAV, etc.)
 - **Language Support**: Multiple target languages for dubbing
 - **Configuration**: Flexible API key and endpoint configuration
-- **Testing**: Comprehensive test suite with integration tests
+- **Testing**: Comprehensive test suite with integration tests

data/README.md

@@ -1,9 +1,8 @@
 # ElevenlabsClient
 
 [![Gem Version](https://badge.fury.io/rb/elevenlabs_client.svg)](https://badge.fury.io/rb/elevenlabs_client)
-[![Build Status](https://github.com/yourusername/elevenlabs_client/workflows/CI/badge.svg)](https://github.com/yourusername/elevenlabs_client/actions)
 
-A comprehensive Ruby client library for the ElevenLabs API, supporting voice synthesis, dubbing, dialogue generation, and sound effects.
+A comprehensive Ruby client library for the ElevenLabs API, supporting voice synthesis, dubbing, dialogue generation, sound effects, and AI music composition.
 
 ## Features
 
@@ -11,6 +10,10 @@ A comprehensive Ruby client library for the ElevenLabs API, supporting voice syn
 🎬 **Dubbing** - Create dubbed versions of audio/video content  
 💬 **Dialogue Generation** - Multi-speaker conversations  
 🔊 **Sound Generation** - AI-generated sound effects and ambient audio  
+🎵 **Music Generation** - AI-powered music composition and streaming  
+🎨 **Voice Design** - Create custom voices from text descriptions  
+🎭 **Voice Management** - Create, edit, and manage individual voices  
+🤖 **Models** - List available models and their capabilities  
 📡 **Streaming** - Real-time audio streaming  
 ⚙️ **Configurable** - Flexible configuration options  
 🧪 **Well-tested** - Comprehensive test coverage  
@@ -106,6 +109,38 @@ audio_data = client.text_to_dialogue.convert(dialogue)
 # Sound Generation
 audio_data = client.sound_generation.generate("Ocean waves crashing on rocks")
 
+# Voice Design
+design_result = client.text_to_voice.design("Warm, professional female voice")
+generated_voice_id = design_result["previews"].first["generated_voice_id"]
+
+voice_result = client.text_to_voice.create(
+  "Professional Voice",
+  "Warm, professional female voice",
+  generated_voice_id
+)
+
+# List Available Models
+models = client.models.list
+fastest_model = models["models"].min_by { |m| m["token_cost_factor"] }
+puts "Fastest model: #{fastest_model['name']}"
+
+# Voice Management
+voices = client.voices.list
+puts "Total voices: #{voices['voices'].length}"
+
+# Create custom voice from audio samples
+File.open("sample1.mp3", "rb") do |sample|
+  voice = client.voices.create("My Voice", [sample], description: "Custom narrator voice")
+  puts "Created voice: #{voice['voice_id']}"
+end
+
+# Music Generation
+music_data = client.music.compose(
+  prompt: "Upbeat electronic dance track with synthesizers",
+  music_length_ms: 30000
+)
+File.open("generated_music.mp3", "wb") { |f| f.write(music_data) }
+
 # Streaming Text-to-Speech
 client.text_to_speech_stream.stream("voice_id", "Streaming text") do |chunk|
   # Process audio chunk in real-time
@@ -122,6 +157,10 @@ end
 - **[Text-to-Speech Streaming API](docs/TEXT_TO_SPEECH_STREAMING.md)** - Real-time audio streaming
 - **[Text-to-Dialogue API](docs/TEXT_TO_DIALOGUE.md)** - Multi-speaker conversations
 - **[Sound Generation API](docs/SOUND_GENERATION.md)** - AI-generated sound effects
+- **[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)
+- **[Models API](docs/MODELS.md)** - List available models and capabilities
 
 ### Available Endpoints
 
@@ -132,6 +171,10 @@ end
 | `client.text_to_speech_stream.*` | Streaming TTS | [TEXT_TO_SPEECH_STREAMING.md](docs/TEXT_TO_SPEECH_STREAMING.md) |
 | `client.text_to_dialogue.*` | Dialogue generation | [TEXT_TO_DIALOGUE.md](docs/TEXT_TO_DIALOGUE.md) |
 | `client.sound_generation.*` | Sound effect generation | [SOUND_GENERATION.md](docs/SOUND_GENERATION.md) |
+| `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.models.*` | Model information and capabilities | [MODELS.md](docs/MODELS.md) |
 
 ## Configuration Options
 
@@ -189,13 +232,16 @@ The gem is designed to work seamlessly with Rails applications. See the [example
 - [StreamingAudioController](examples/streaming_audio_controller.rb) - Real-time streaming
 - [TextToDialogueController](examples/text_to_dialogue_controller.rb) - Dialogue generation
 - [SoundGenerationController](examples/sound_generation_controller.rb) - Sound effects
+- [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)
 
 ## Development
 
 After checking out the repo, run:
 
 ```bash
-bin/setup      # Install dependencies
+bin/setup          # Install dependencies
 bundle exec rspec  # Run tests
 ```
 
@@ -221,6 +267,7 @@ bundle exec rspec
 
 # Run specific test files
 bundle exec rspec spec/elevenlabs_client/endpoints/
+bundle exec rspec spec/elevenlabs_client/client
 bundle exec rspec spec/integration/
 
 # Run with documentation format

data/lib/elevenlabs_client/client.rb

@@ -7,7 +7,7 @@ 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
+    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
 
     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)
@@ -18,6 +18,10 @@ module ElevenlabsClient
       @text_to_speech_stream = TextToSpeechStream.new(self)
       @text_to_dialogue = TextToDialogue.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)
     end
 
     # Makes an authenticated GET request
@@ -39,7 +43,33 @@ module ElevenlabsClient
     def post(path, body = nil)
       response = @conn.post(path) do |req|
         req.headers["xi-api-key"] = api_key
-        req.body = body if body
+        req.headers["Content-Type"] = "application/json"
+        req.body = body.to_json if body
+      end
+
+      handle_response(response)
+    end
+
+    # Makes an authenticated DELETE request
+    # @param path [String] API endpoint path
+    # @return [Hash] Response body
+    def delete(path)
+      response = @conn.delete(path) do |req|
+        req.headers["xi-api-key"] = api_key
+      end
+
+      handle_response(response)
+    end
+
+    # Makes an authenticated PATCH request
+    # @param path [String] API endpoint path
+    # @param body [Hash, nil] Request body
+    # @return [Hash] Response body
+    def patch(path, body = nil)
+      response = @conn.patch(path) do |req|
+        req.headers["xi-api-key"] = api_key
+        req.headers["Content-Type"] = "application/json"
+        req.body = body.to_json if body
       end
 
       handle_response(response)
@@ -69,7 +99,7 @@ module ElevenlabsClient
         req.body = body.to_json if body
       end
 
-      handle_binary_response(response)
+      handle_response(response)
     end
 
     # Makes an authenticated POST request with custom headers
@@ -87,7 +117,7 @@ module ElevenlabsClient
 
       # For streaming/binary responses, return raw body
       if custom_headers["Accept"]&.include?("audio") || custom_headers["Transfer-Encoding"] == "chunked"
-        handle_binary_response(response)
+        handle_response(response)
       else
         handle_response(response)
       end
@@ -111,7 +141,7 @@ module ElevenlabsClient
         end
       end
 
-      handle_streaming_response(response)
+      handle_response(response)
     end
 
     # Helper method to create Faraday::Multipart::FilePart
@@ -157,44 +187,58 @@ module ElevenlabsClient
       case response.status
       when 200..299
         response.body
+      when 400
+        error_message = extract_error_message(response.body)
+        raise BadRequestError, error_message.empty? ? "Bad request - invalid parameters" : error_message
       when 401
-        raise AuthenticationError, "Invalid API key or authentication failed"
+        error_message = extract_error_message(response.body)
+        raise AuthenticationError, error_message.empty? ? "Invalid API key or authentication failed" : error_message
+      when 404
+        error_message = extract_error_message(response.body)
+        raise NotFoundError, error_message.empty? ? "Resource not found" : error_message
+      when 422
+        error_message = extract_error_message(response.body)
+        raise UnprocessableEntityError, error_message.empty? ? "Unprocessable entity - invalid data" : error_message
       when 429
-        raise RateLimitError, "Rate limit exceeded"
+        error_message = extract_error_message(response.body)
+        raise RateLimitError, error_message.empty? ? "Rate limit exceeded" : error_message
       when 400..499
-        raise ValidationError, response.body.inspect
+        error_message = extract_error_message(response.body)
+        raise ValidationError, error_message.empty? ? "Client error occurred with status #{response.status}" : error_message
       else
-        raise APIError, "API request failed with status #{response.status}: #{response.body.inspect}"
+        error_message = extract_error_message(response.body)
+        raise APIError, error_message.empty? ? "API request failed with status #{response.status}" : error_message
       end
     end
 
-    def handle_binary_response(response)
-      case response.status
-      when 200..299
-        response.body
-      when 401
-        raise AuthenticationError, "Invalid API key or authentication failed"
-      when 429
-        raise RateLimitError, "Rate limit exceeded"
-      when 400..499
-        raise ValidationError, "API request failed with status #{response.status}"
-      else
-        raise APIError, "API request failed with status #{response.status}"
-      end
-    end
+    private
 
-    def handle_streaming_response(response)
-      case response.status
-      when 200..299
-        response
-      when 401
-        raise AuthenticationError, "Invalid API key or authentication failed"
-      when 429
-        raise RateLimitError, "Rate limit exceeded"
-      when 400..499
-        raise ValidationError, "API request failed with status #{response.status}"
-      else
-        raise APIError, "API request failed with status #{response.status}"
+    def extract_error_message(response_body)
+      return "" if response_body.nil? || response_body.empty?
+      
+      # Handle non-string response bodies
+      body_str = response_body.is_a?(String) ? response_body : response_body.to_s
+      
+      begin
+        error_info = JSON.parse(body_str)
+        
+        # Try different common error message fields
+        message = error_info["detail"] || 
+                 error_info["message"] || 
+                 error_info["error"] ||
+                 error_info["errors"]
+        
+        # Handle nested detail objects
+        if message.is_a?(Hash)
+          message = message["message"] || message.to_s
+        elsif message.is_a?(Array)
+          message = message.first.to_s
+        end
+        
+        message.to_s
+      rescue JSON::ParserError, TypeError
+        # If not JSON or can't be parsed, return the raw body (truncated if too long)
+        body_str.length > 200 ? "#{body_str[0..200]}..." : body_str
       end
     end
 

data/lib/elevenlabs_client/endpoints/dubs.rb

@@ -53,6 +53,162 @@ module ElevenlabsClient
       @client.get("/v1/dubbing/#{dubbing_id}/resources")
     end
 
+    # DELETE /v1/dubbing/{id}
+    # Deletes a dubbing project
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @return [Hash] Response with status
+    def delete(dubbing_id)
+      @client.delete("/v1/dubbing/#{dubbing_id}")
+    end
+
+    # GET /v1/dubbing/resource/{dubbing_id}
+    # Gets dubbing resource with detailed information including segments, speakers, etc.
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @return [Hash] Detailed dubbing resource information
+    def get_resource(dubbing_id)
+      @client.get("/v1/dubbing/resource/#{dubbing_id}")
+    end
+
+    # POST /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}/segment
+    # Creates a new segment in dubbing resource
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param speaker_id [String] The speaker ID
+    # @param start_time [Float] Start time of the segment
+    # @param end_time [Float] End time of the segment
+    # @param text [String, nil] Optional text for the segment
+    # @param translations [Hash, nil] Optional translations map
+    # @return [Hash] Response with version and new segment ID
+    def create_segment(dubbing_id:, speaker_id:, start_time:, end_time:, text: nil, translations: nil)
+      payload = {
+        start_time: start_time,
+        end_time: end_time,
+        text: text,
+        translations: translations
+      }.compact
+
+      @client.post("/v1/dubbing/resource/#{dubbing_id}/speaker/#{speaker_id}/segment", payload)
+    end
+
+    # DELETE /v1/dubbing/resource/{dubbing_id}/segment/{segment_id}
+    # Deletes a single segment from the dubbing
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param segment_id [String] The segment ID
+    # @return [Hash] Response with version
+    def delete_segment(dubbing_id, segment_id)
+      @client.delete("/v1/dubbing/resource/#{dubbing_id}/segment/#{segment_id}")
+    end
+
+    # PATCH /v1/dubbing/resource/{dubbing_id}/segment/{segment_id}/{language}
+    # Updates a single segment with new text and/or start/end times
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param segment_id [String] The segment ID
+    # @param language [String] The language ID
+    # @param start_time [Float, nil] Optional new start time
+    # @param end_time [Float, nil] Optional new end time
+    # @param text [String, nil] Optional new text
+    # @return [Hash] Response with version
+    def update_segment(dubbing_id:, segment_id:, language:, start_time: nil, end_time: nil, text: nil)
+      payload = {
+        start_time: start_time,
+        end_time: end_time,
+        text: text
+      }.compact
+
+      @client.patch("/v1/dubbing/resource/#{dubbing_id}/segment/#{segment_id}/#{language}", payload)
+    end
+
+    # POST /v1/dubbing/resource/{dubbing_id}/transcribe
+    # Regenerates transcriptions for specified segments
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param segments [Array<String>] List of segment IDs to transcribe
+    # @return [Hash] Response with version
+    def transcribe_segment(dubbing_id, segments)
+      payload = { segments: segments }
+      @client.post("/v1/dubbing/resource/#{dubbing_id}/transcribe", payload)
+    end
+
+    # POST /v1/dubbing/resource/{dubbing_id}/translate
+    # Regenerates translations for specified segments/languages
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param segments [Array<String>] List of segment IDs to translate
+    # @param languages [Array<String>, nil] Optional list of languages to translate
+    # @return [Hash] Response with version
+    def translate_segment(dubbing_id, segments, languages = nil)
+      payload = {
+        segments: segments,
+        languages: languages
+      }.compact
+
+      @client.post("/v1/dubbing/resource/#{dubbing_id}/translate", payload)
+    end
+
+    # POST /v1/dubbing/resource/{dubbing_id}/dub
+    # Regenerates dubs for specified segments/languages
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param segments [Array<String>] List of segment IDs to dub
+    # @param languages [Array<String>, nil] Optional list of languages to dub
+    # @return [Hash] Response with version
+    def dub_segment(dubbing_id, segments, languages = nil)
+      payload = {
+        segments: segments,
+        languages: languages
+      }.compact
+
+      @client.post("/v1/dubbing/resource/#{dubbing_id}/dub", payload)
+    end
+
+    # POST /v1/dubbing/resource/{dubbing_id}/render/{language}
+    # Renders the output media for a language
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param language [String] The language to render
+    # @param render_type [String] The type of render (mp4, aac, mp3, wav, aaf, tracks_zip, clips_zip)
+    # @param normalize_volume [Boolean, nil] Whether to normalize volume (defaults to false)
+    # @return [Hash] Response with version and render_id
+    def render_project(dubbing_id:, language:, render_type:, normalize_volume: nil)
+      payload = {
+        render_type: render_type,
+        normalize_volume: normalize_volume
+      }.compact
+
+      @client.post("/v1/dubbing/resource/#{dubbing_id}/render/#{language}", payload)
+    end
+
+    # PATCH /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}
+    # Updates speaker metadata such as voice
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param speaker_id [String] The speaker ID
+    # @param voice_id [String, nil] Voice ID from library or 'track-clone'/'clip-clone'
+    # @param languages [Array<String>, nil] Languages to apply changes to
+    # @return [Hash] Response with version
+    def update_speaker(dubbing_id:, speaker_id:, voice_id: nil, languages: nil)
+      payload = {
+        voice_id: voice_id,
+        languages: languages
+      }.compact
+
+      @client.patch("/v1/dubbing/resource/#{dubbing_id}/speaker/#{speaker_id}", payload)
+    end
+
+    # GET /v1/dubbing/resource/{dubbing_id}/speaker/{speaker_id}/similar-voices
+    # Gets similar voices for a speaker
+    #
+    # @param dubbing_id [String] The dubbing job ID
+    # @param speaker_id [String] The speaker ID
+    # @return [Hash] Response with list of similar voices
+    def get_similar_voices(dubbing_id, speaker_id)
+      @client.get("/v1/dubbing/resource/#{dubbing_id}/speaker/#{speaker_id}/similar-voices")
+    end
+
     private
 
     attr_reader :client

data/lib/elevenlabs_client/endpoints/models.rb

@@ -0,0 +1,26 @@
+# 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/music.rb

@@ -0,0 +1,127 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  module Endpoints
+    class Music
+      def initialize(client)
+        @client = client
+      end
+
+      # POST /v1/music
+      # Compose music and return binary audio data
+      # Documentation: https://elevenlabs.io/docs/api-reference/music/compose
+      #
+      # @param options [Hash] Music composition parameters
+      # @option options [String] :prompt Text description of the music to generate
+      # @option options [Hash] :composition_plan Detailed composition structure (optional)
+      # @option options [Integer] :music_length_ms Length of music in milliseconds (optional)
+      # @option options [String] :model_id Model to use for generation (default: "music_v1")
+      # @option options [String] :output_format Audio format (e.g., "mp3_44100_128")
+      # @return [String] Binary audio data
+      def compose(options = {})
+        endpoint = "/v1/music"
+        request_body = build_music_request_body(options)
+        
+        query_params = {}
+        query_params[:output_format] = options[:output_format] if options[:output_format]
+        
+        endpoint_with_query = query_params.empty? ? endpoint : "#{endpoint}?#{URI.encode_www_form(query_params)}"
+        
+        @client.post_binary(endpoint_with_query, request_body)
+      end
+
+      # POST /v1/music/stream
+      # Compose music with streaming audio response
+      # Documentation: https://elevenlabs.io/docs/api-reference/music/compose-stream
+      #
+      # @param options [Hash] Music composition parameters
+      # @option options [String] :prompt Text description of the music to generate
+      # @option options [Hash] :composition_plan Detailed composition structure (optional)
+      # @option options [Integer] :music_length_ms Length of music in milliseconds (optional)
+      # @option options [String] :model_id Model to use for generation (default: "music_v1")
+      # @option options [String] :output_format Audio format (e.g., "mp3_44100_128")
+      # @param block [Proc] Block to handle streaming audio chunks
+      # @return [nil] Audio is streamed via the block
+      def compose_stream(options = {}, &block)
+        endpoint = "/v1/music/stream"
+        request_body = build_music_request_body(options)
+        
+        query_params = {}
+        query_params[:output_format] = options[:output_format] if options[:output_format]
+        
+        endpoint_with_query = query_params.empty? ? endpoint : "#{endpoint}?#{URI.encode_www_form(query_params)}"
+        
+        @client.post_streaming(endpoint_with_query, request_body, &block)
+      end
+
+      # POST /v1/music/detailed
+      # Compose music and return detailed response with metadata and audio
+      # Documentation: https://elevenlabs.io/docs/api-reference/music/compose-detailed
+      #
+      # @param options [Hash] Music composition parameters
+      # @option options [String] :prompt Text description of the music to generate
+      # @option options [Hash] :composition_plan Detailed composition structure (optional)
+      # @option options [Integer] :music_length_ms Length of music in milliseconds (optional)
+      # @option options [String] :model_id Model to use for generation (default: "music_v1")
+      # @option options [String] :output_format Audio format (e.g., "mp3_44100_128")
+      # @return [String] Multipart response with JSON metadata and binary audio
+      def compose_detailed(options = {})
+        endpoint = "/v1/music/detailed"
+        request_body = build_music_request_body(options)
+        
+        query_params = {}
+        query_params[:output_format] = options[:output_format] if options[:output_format]
+        
+        endpoint_with_query = query_params.empty? ? endpoint : "#{endpoint}?#{URI.encode_www_form(query_params)}"
+        
+        # Use post_with_custom_headers to handle multipart response
+        @client.post_with_custom_headers(
+          endpoint_with_query,
+          request_body,
+          { "Accept" => "multipart/mixed" }
+        )
+      end
+
+      # POST /v1/music/plan
+      # Create a composition plan for music generation
+      # Documentation: https://elevenlabs.io/docs/api-reference/music/create-plan
+      #
+      # @param options [Hash] Plan creation parameters
+      # @option options [String] :prompt Text description of the music style/structure
+      # @option options [Integer] :music_length_ms Desired length of music in milliseconds
+      # @option options [Hash] :source_composition_plan Base plan to modify (optional)
+      # @option options [String] :model_id Model to use for plan generation (default: "music_v1")
+      # @return [Hash] JSON response containing the composition plan
+      def create_plan(options = {})
+        endpoint = "/v1/music/plan"
+        request_body = {
+          prompt: options[:prompt],
+          music_length_ms: options[:music_length_ms],
+          source_composition_plan: options[:source_composition_plan],
+          model_id: options[:model_id] || "music_v1"
+        }.compact
+        
+        @client.post(endpoint, request_body)
+      end
+
+      # Alias methods for convenience
+      alias_method :compose_music, :compose
+      alias_method :compose_music_stream, :compose_stream
+      alias_method :compose_music_detailed, :compose_detailed
+      alias_method :create_music_plan, :create_plan
+
+      private
+
+      attr_reader :client
+
+      def build_music_request_body(options)
+        {
+          prompt: options[:prompt],
+          composition_plan: options[:composition_plan],
+          music_length_ms: options[:music_length_ms],
+          model_id: options[:model_id] || "music_v1"
+        }.compact
+      end
+    end
+  end
+end

data/lib/elevenlabs_client/endpoints/text_to_voice.rb

@@ -0,0 +1,95 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class TextToVoice
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/text-to-voice/design
+    # Designs a voice based on a description
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-voice/design
+    #
+    # @param voice_description [String] Description of the voice (20-1000 characters)
+    # @param options [Hash] Optional parameters
+    # @option options [String] :output_format Output format (e.g., "mp3_44100_192")
+    # @option options [String] :model_id Model to use (e.g., "eleven_multilingual_ttv_v2", "eleven_ttv_v3")
+    # @option options [String] :text Text to generate (100-1000 characters, optional)
+    # @option options [Boolean] :auto_generate_text Auto-generate text (default: false)
+    # @option options [Float] :loudness Loudness level (-1 to 1, default: 0.5)
+    # @option options [Integer] :seed Random seed (0 to 2147483647, optional)
+    # @option options [Float] :guidance_scale Guidance scale (0 to 100, default: 5)
+    # @option options [Boolean] :stream_previews Stream previews (default: false)
+    # @option options [String] :remixing_session_id Remixing session ID (optional)
+    # @option options [String] :remixing_session_iteration_id Remixing session iteration ID (optional)
+    # @option options [Float] :quality Quality level (-1 to 1, optional)
+    # @option options [String] :reference_audio_base64 Base64 encoded reference audio (optional, requires eleven_ttv_v3)
+    # @option options [Float] :prompt_strength Prompt strength (0 to 1, optional, requires eleven_ttv_v3)
+    # @return [Hash] JSON response containing previews and text
+    def design(voice_description, **options)
+      endpoint = "/v1/text-to-voice/design"
+      request_body = { voice_description: voice_description }
+
+      # Add optional parameters if provided
+      request_body[:output_format] = options[:output_format] if options[:output_format]
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:text] = options[:text] if options[:text]
+      request_body[:auto_generate_text] = options[:auto_generate_text] unless options[:auto_generate_text].nil?
+      request_body[:loudness] = options[:loudness] if options[:loudness]
+      request_body[:seed] = options[:seed] if options[:seed]
+      request_body[:guidance_scale] = options[:guidance_scale] if options[:guidance_scale]
+      request_body[:stream_previews] = options[:stream_previews] unless options[:stream_previews].nil?
+      request_body[:remixing_session_id] = options[:remixing_session_id] if options[:remixing_session_id]
+      request_body[:remixing_session_iteration_id] = options[:remixing_session_iteration_id] if options[:remixing_session_iteration_id]
+      request_body[:quality] = options[:quality] if options[:quality]
+      request_body[:reference_audio_base64] = options[:reference_audio_base64] if options[:reference_audio_base64]
+      request_body[:prompt_strength] = options[:prompt_strength] if options[:prompt_strength]
+
+      @client.post(endpoint, request_body)
+    end
+
+    # POST /v1/text-to-voice
+    # Creates a voice from the designed voice generated_voice_id
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-voice
+    #
+    # @param voice_name [String] Name of the voice
+    # @param voice_description [String] Description of the voice (20-1000 characters)
+    # @param generated_voice_id [String] The generated voice ID from design_voice
+    # @param options [Hash] Optional parameters
+    # @option options [Hash] :labels Optional metadata for the voice
+    # @option options [Array<String>] :played_not_selected_voice_ids Optional list of voice IDs played but not selected
+    # @return [Hash] JSON response containing voice_id and other voice details
+    def create(voice_name, voice_description, generated_voice_id, **options)
+      endpoint = "/v1/text-to-voice"
+      request_body = {
+        voice_name: voice_name,
+        voice_description: voice_description,
+        generated_voice_id: generated_voice_id
+      }
+
+      # Add optional parameters if provided
+      request_body[:labels] = options[:labels] if options[:labels]
+      request_body[:played_not_selected_voice_ids] = options[:played_not_selected_voice_ids] if options[:played_not_selected_voice_ids]
+
+      @client.post(endpoint, request_body)
+    end
+
+    # GET /v1/voices
+    # Retrieves all voices associated with your Elevenlabs account
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices
+    #
+    # @return [Hash] The JSON response containing an array of voices
+    def list_voices
+      endpoint = "/v1/voices"
+      @client.get(endpoint)
+    end
+
+    # Alias methods for backward compatibility and convenience
+    alias_method :design_voice, :design
+    alias_method :create_from_generated_voice, :create
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/voices.rb

@@ -0,0 +1,147 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class Voices
+    def initialize(client)
+      @client = client
+    end
+
+    # GET /v1/voices/{voice_id}
+    # Retrieves details about a single voice
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices/get-voice
+    #
+    # @param voice_id [String] The ID of the voice to retrieve
+    # @return [Hash] Details of the voice
+    def get(voice_id)
+      endpoint = "/v1/voices/#{voice_id}"
+      @client.get(endpoint)
+    end
+
+    # GET /v1/voices
+    # Retrieves all voices associated with your Elevenlabs account
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices
+    #
+    # @return [Hash] The JSON response containing an array of voices
+    def list
+      endpoint = "/v1/voices"
+      @client.get(endpoint)
+    end
+
+    # POST /v1/voices/add
+    # Creates a new voice by cloning from audio samples
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices/add-voice
+    #
+    # @param name [String] Name of the voice
+    # @param samples [Array<File, IO>] Array of audio files to train the voice
+    # @param options [Hash] Additional parameters
+    # @option options [String] :description Description of the voice
+    # @option options [Hash] :labels Metadata labels for the voice
+    # @return [Hash] Response containing the new voice details
+    def create(name, samples = [], **options)
+      endpoint = "/v1/voices/add"
+      
+      # Build multipart payload
+      payload = {
+        "name" => name,
+        "description" => options[:description] || ""
+      }
+
+      # Add labels if provided
+      if options[:labels]
+        options[:labels].each do |key, value|
+          payload["labels[#{key}]"] = value.to_s
+        end
+      end
+
+      # Add sample files
+      samples.each_with_index do |sample, index|
+        payload["files"] = @client.file_part(sample, "audio/mpeg")
+      end
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # POST /v1/voices/{voice_id}/edit
+    # Updates an existing voice
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices/edit-voice
+    #
+    # @param voice_id [String] The ID of the voice to edit
+    # @param samples [Array<File, IO>] Array of audio files (optional)
+    # @param options [Hash] Voice parameters to update
+    # @option options [String] :name New name for the voice
+    # @option options [String] :description New description for the voice
+    # @option options [Hash] :labels New labels for the voice
+    # @return [Hash] Response containing the updated voice details
+    def edit(voice_id, samples = [], **options)
+      endpoint = "/v1/voices/#{voice_id}/edit"
+      
+      # Build multipart payload
+      payload = {}
+      
+      # Add text fields if provided
+      payload["name"] = options[:name] if options[:name]
+      payload["description"] = options[:description] if options[:description]
+
+      # Add labels if provided
+      if options[:labels]
+        options[:labels].each do |key, value|
+          payload["labels[#{key}]"] = value.to_s
+        end
+      end
+
+      # Add sample files if provided
+      if samples && !samples.empty?
+        samples.each_with_index do |sample, index|
+          payload["files"] = @client.file_part(sample, "audio/mpeg")
+        end
+      end
+
+      @client.post_multipart(endpoint, payload)
+    end
+
+    # DELETE /v1/voices/{voice_id}
+    # Deletes a voice from your account
+    # Documentation: https://elevenlabs.io/docs/api-reference/voices/delete-voice
+    #
+    # @param voice_id [String] The ID of the voice to delete
+    # @return [Hash] Response confirming deletion
+    def delete(voice_id)
+      endpoint = "/v1/voices/#{voice_id}"
+      @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
+
+    # Alias methods for backward compatibility and convenience
+    alias_method :get_voice, :get
+    alias_method :list_voices, :list
+    alias_method :create_voice, :create
+    alias_method :edit_voice, :edit
+    alias_method :delete_voice, :delete
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/errors.rb

@@ -6,4 +6,7 @@ module ElevenlabsClient
   class AuthenticationError < Error; end
   class RateLimitError < Error; end
   class ValidationError < Error; end
+  class NotFoundError < Error; end
+  class BadRequestError < Error; end
+  class UnprocessableEntityError < Error; end
 end

data/lib/elevenlabs_client/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ElevenlabsClient
-  VERSION = "0.2.0"
+  VERSION = "0.4.0"
 end

data/lib/elevenlabs_client.rb

@@ -8,6 +8,10 @@ require_relative "elevenlabs_client/endpoints/text_to_speech"
 require_relative "elevenlabs_client/endpoints/text_to_speech_stream"
 require_relative "elevenlabs_client/endpoints/text_to_dialogue"
 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/voices"
+require_relative "elevenlabs_client/endpoints/music"
 require_relative "elevenlabs_client/client"
 
 module ElevenlabsClient

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: elevenlabs_client
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Vitor Oliveira
@@ -122,10 +122,14 @@ files:
 - lib/elevenlabs_client.rb
 - lib/elevenlabs_client/client.rb
 - lib/elevenlabs_client/endpoints/dubs.rb
+- lib/elevenlabs_client/endpoints/models.rb
+- lib/elevenlabs_client/endpoints/music.rb
 - lib/elevenlabs_client/endpoints/sound_generation.rb
 - lib/elevenlabs_client/endpoints/text_to_dialogue.rb
 - lib/elevenlabs_client/endpoints/text_to_speech.rb
 - lib/elevenlabs_client/endpoints/text_to_speech_stream.rb
+- lib/elevenlabs_client/endpoints/text_to_voice.rb
+- lib/elevenlabs_client/endpoints/voices.rb
 - lib/elevenlabs_client/errors.rb
 - lib/elevenlabs_client/settings.rb
 - lib/elevenlabs_client/version.rb