elevenlabs_client 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 244f4e543adab6725041a23c4742e95b32e6352635496ecf7ea3dbb7ae518d8b
-  data.tar.gz: 0f4444f50015137e1627a82edc7b9a6159a5dc4bdb41de521c8d2609130d642c
+  metadata.gz: 2eb4466ffb626d55734bcd3569141c50293bbee7219fcffc252bd161f3bacac5
+  data.tar.gz: 2b045b85c15865d17f000a924c2f5088558d81f85b50e1273a11b6950e4eda9f
 SHA512:
-  metadata.gz: 4fda1901bc041645ef289c56bc1474ae9f5e3c9ec965dc70371271344b5412c799c8e9fb519d28d780b1c26de32b7318abc63b2d0d0681337fd004ec53e48179
-  data.tar.gz: 92dc43058342c80fd0c72d66d8936fac2d66f1a38c31d606481a40c244bc8c8cd1cfc452f959e1dc014b514c2a56135a40e103166c53d1cbd3c1d15e0f3849fd
+  metadata.gz: 30cfe941d5a311175436c55e5952d743efaa42410fc38e3e2c6df5c1b8db374720d960f86cc57c8985127028b6bc9312a360d4744e7536913576a1ce4c3bbb9e
+  data.tar.gz: ec656950468c78eede815ae879c1e7475e6c8d64d725a850c4d6ebf95f7ce9c058174b734a4cec19c4c65133ede31aac0b57f08b271e17ce6a87904c2609e3e3

data/CHANGELOG.md

@@ -7,6 +7,84 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.0] - 2025-09-12
+
+### Added
+- **Text-to-Speech API** - Convert text to natural-sounding speech with voice customization
+- **Text-to-Speech Streaming API** - Real-time audio streaming for live applications
+- **Text-to-Dialogue API** - Multi-speaker conversation generation
+- **Sound Generation API** - AI-generated sound effects and ambient audio
+- **Comprehensive Documentation** - Separate documentation files for each API endpoint
+- **Rails Integration Examples** - Complete controller examples for all endpoints
+- **Enhanced Configuration** - Flexible configuration with Settings module
+- **Streaming Support** - Real-time audio chunk processing with block callbacks
+- **Binary Response Handling** - Proper handling of audio data responses
+- **Query Parameter Support** - URL query parameters for API requests
+
+### Enhanced
+- **Endpoint Organization** - Moved all endpoints to dedicated `lib/elevenlabs_client/endpoints/` directory
+- **Client Architecture** - Separated HTTP client logic from endpoint-specific functionality
+- **Error Handling** - Enhanced error handling with streaming-specific exceptions
+- **Test Coverage** - Expanded test suite to 187+ tests covering all new functionality
+- **Configuration System** - Priority-based configuration (explicit > Settings > ENV)
+
+### Documentation
+- **Modular Documentation** - Split endpoint documentation into separate files:
+  - [DUBBING.md](docs/DUBBING.md) - Audio/video dubbing functionality
+  - [TEXT_TO_SPEECH.md](docs/TEXT_TO_SPEECH.md) - Text-to-speech conversion
+  - [TEXT_TO_SPEECH_STREAMING.md](docs/TEXT_TO_SPEECH_STREAMING.md) - Real-time streaming
+  - [TEXT_TO_DIALOGUE.md](docs/TEXT_TO_DIALOGUE.md) - Multi-speaker dialogues
+  - [SOUND_GENERATION.md](docs/SOUND_GENERATION.md) - Sound effect generation
+- **Improved README** - Streamlined main README with quick start guide
+- **Rails Examples** - Complete controller implementations for all endpoints
+- **Usage Examples** - Comprehensive examples for each API feature
+
+### New Endpoints
+- `client.text_to_speech.*` - Text-to-speech conversion with voice settings
+- `client.text_to_speech_stream.*` - Real-time streaming text-to-speech
+- `client.text_to_dialogue.*` - Multi-speaker dialogue generation
+- `client.sound_generation.*` - AI sound effect and ambient audio generation
+
+### New Features
+- **Voice Customization** - Stability, similarity boost, style controls
+- **Audio Formats** - Multiple output formats (MP3, PCM) with quality options
+- **Looping Audio** - Generate seamless looping sound effects
+- **Deterministic Generation** - Seed support for consistent results
+- **Batch Processing** - Multiple sound generation in single requests
+- **WebSocket Integration** - Real-time streaming to WebSocket connections
+- **File Format Support** - Enhanced support for various audio/video formats
+
+### Technical Improvements
+- **Modular Architecture** - Clean separation of concerns with endpoint classes
+- **HTTP Client Enhancement** - Added streaming, binary, and custom header support
+- **Settings Management** - Centralized configuration with Rails initializer support
+- **Memory Management** - Efficient handling of large audio files and streams
+- **Concurrent Testing** - Parallel test execution for faster development
+
+### Examples Added
+- `examples/dubs_controller.rb` - Complete dubbing workflow with batch processing
+- `examples/text_to_speech_controller.rb` - TTS with voice customization
+- `examples/streaming_audio_controller.rb` - Real-time streaming with WebSocket support
+- `examples/text_to_dialogue_controller.rb` - Specialized dialogue endpoints
+- `examples/sound_generation_controller.rb` - Sound effects with presets and batch processing
+- `examples/rails_initializer.rb` - Rails configuration example
+
+### Breaking Changes
+- **Endpoint Access** - Dubbing methods moved from `client.create_dub` to `client.dubs.create`
+- **File Structure** - Endpoint classes moved to `lib/elevenlabs_client/endpoints/`
+- **Configuration** - Enhanced configuration system with new precedence rules
+
+### Migration Guide
+```ruby
+# Before (v0.1.0)
+client.create_dub(file_io: file, filename: "video.mp4", target_languages: ["es"])
+
+# After (v0.2.0)
+client.dubs.create(file_io: file, filename: "video.mp4", target_languages: ["es"])
+```
+
+## [0.1.0] - 2025-09-12
+
 ### Added
 - Initial release of ElevenLabs Client gem
 - Support for ElevenLabs Dubbing API
@@ -26,12 +104,4 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **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
-
-## [0.1.0] - 2025-01-XX
-
-### Added
-- Initial implementation of ElevenLabs Client
-- Basic dubbing functionality
-- Error handling and validation
-- Documentation and examples
+- **Testing**: Comprehensive test suite with integration tests

data/README.md

@@ -1,24 +1,45 @@
 # ElevenlabsClient
 
-A Ruby client library for interacting with ElevenLabs APIs, including dubbing and voice synthesis.
+[![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.
+
+## Features
+
+🎙️ **Text-to-Speech** - Convert text to natural-sounding speech  
+🎬 **Dubbing** - Create dubbed versions of audio/video content  
+💬 **Dialogue Generation** - Multi-speaker conversations  
+🔊 **Sound Generation** - AI-generated sound effects and ambient audio  
+📡 **Streaming** - Real-time audio streaming  
+⚙️ **Configurable** - Flexible configuration options  
+🧪 **Well-tested** - Comprehensive test coverage  
 
 ## Installation
 
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'elevenlabs_client', path: 'lib/elevenlabs_client'
+gem 'elevenlabs_client'
 ```
 
 And then execute:
 
-    $ bundle install
+```bash
+$ bundle install
+```
+
+Or install it yourself as:
+
+```bash
+$ gem install elevenlabs_client
+```
 
-## Usage
+## Quick Start
 
 ### Configuration
 
-#### Rails Initializer (Recommended for Rails apps)
+#### Rails Applications (Recommended)
 
 Create `config/initializers/elevenlabs_client.rb`:
 
@@ -26,149 +47,210 @@ Create `config/initializers/elevenlabs_client.rb`:
 ElevenlabsClient::Settings.configure do |config|
   config.properties = {
     elevenlabs_base_uri: ENV["ELEVENLABS_BASE_URL"],
-    elevenlabs_api_key: ENV["ELEVENLABS_API_KEY"],
+    elevenlabs_api_key: ENV["ELEVENLABS_API_KEY"]
   }
 end
 ```
 
-Once configured this way, you can create clients without passing any parameters:
+Set your environment variables:
 
-```ruby
-client = ElevenlabsClient.new
-# Uses the configured settings automatically
+```bash
+export ELEVENLABS_API_KEY="your_api_key_here"
+export ELEVENLABS_BASE_URL="https://api.elevenlabs.io"  # Optional, defaults to official API
 ```
 
-#### Alternative Configuration Syntax
-
-You can also use the module-level configure method:
+#### Direct Configuration
 
 ```ruby
+# Module-level configuration
 ElevenlabsClient.configure do |config|
   config.properties = {
     elevenlabs_base_uri: "https://api.elevenlabs.io",
     elevenlabs_api_key: "your_api_key_here"
   }
 end
-```
-
-#### Configuration Precedence
-
-The client uses the following precedence order for configuration:
-
-1. **Explicit parameters** passed to `Client.new` (highest priority)
-2. **Settings.properties** configured via initializer
-3. **Environment variables** (lowest priority)
-
-This allows you to set defaults in your initializer while still being able to override them when needed.
 
-### Client Initialization
-
-There are several ways to create a client:
-
-```ruby
-# Using environment variables (default behavior)
-client = ElevenlabsClient.new
-
-# Passing API key directly
-client = ElevenlabsClient::Client.new(api_key: "your_api_key_here")
-
-# Custom base URL
-client = ElevenlabsClient::Client.new(
+# Or pass directly to client
+client = ElevenlabsClient.new(
   api_key: "your_api_key_here",
-  base_url: "https://custom-api.elevenlabs.io"
-)
-
-# Custom environment variable names
-client = ElevenlabsClient::Client.new(
-  api_key_env: "MY_CUSTOM_API_KEY_VAR",
-  base_url_env: "MY_CUSTOM_BASE_URL_VAR"
+  base_url: "https://api.elevenlabs.io"
 )
 ```
 
 ### Basic Usage
 
 ```ruby
-require 'elevenlabs_client'
-
-# Create a client
+# Initialize client (uses configured settings)
 client = ElevenlabsClient.new
 
-# Create a dubbing job
+# Text-to-Speech
+audio_data = client.text_to_speech.convert("21m00Tcm4TlvDq8ikWAM", "Hello, world!")
+File.open("hello.mp3", "wb") { |f| f.write(audio_data) }
+
+# Dubbing
 File.open("video.mp4", "rb") do |file|
   result = client.dubs.create(
     file_io: file,
     filename: "video.mp4",
-    target_languages: ["es", "pt", "fr"],
-    name: "My Video Dub",
-    drop_background_audio: true,
-    use_profanity_filter: false
+    target_languages: ["es", "fr", "de"]
   )
-  
-  puts "Dubbing job created: #{result['dubbing_id']}"
 end
 
-# Check dubbing status
-dub_details = client.dubs.get("dubbing_id_here")
-puts "Status: #{dub_details['status']}"
+# Dialogue Generation
+dialogue = [
+  { text: "Hello, how are you?", voice_id: "voice_1" },
+  { text: "I'm doing great, thanks!", voice_id: "voice_2" }
+]
+audio_data = client.text_to_dialogue.convert(dialogue)
 
-# List all dubbing jobs
-dubs = client.dubs.list(dubbing_status: "dubbed")
-puts "Completed dubs: #{dubs['dubs'].length}"
+# Sound Generation
+audio_data = client.sound_generation.generate("Ocean waves crashing on rocks")
 
-# Get dubbing resources (for editing)
-resources = client.dubs.resources("dubbing_id_here")
-puts "Audio files: #{resources['resources']['audio_files']}"
+# Streaming Text-to-Speech
+client.text_to_speech_stream.stream("voice_id", "Streaming text") do |chunk|
+  # Process audio chunk in real-time
+  puts "Received #{chunk.bytesize} bytes"
+end
 ```
 
-### Available Dubbing Methods
+## API Documentation
+
+### Core APIs
 
-The client provides access to all dubbing endpoints through the `client.dubs` interface:
+- **[Dubbing API](docs/DUBBING.md)** - Create dubbed versions of audio/video content
+- **[Text-to-Speech API](docs/TEXT_TO_SPEECH.md)** - Convert text to natural speech
+- **[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
 
-- `client.dubs.create(file_io:, filename:, target_languages:, **options)` - Create a new dubbing job
-- `client.dubs.get(dubbing_id)` - Get dubbing job details
-- `client.dubs.list(params = {})` - List dubbing jobs with optional filters
-- `client.dubs.resources(dubbing_id)` - Get dubbing resources for editing
+### Available Endpoints
 
-## Supported Language Codes
+| Endpoint | Description | Documentation |
+|----------|-------------|---------------|
+| `client.dubs.*` | Audio/video dubbing | [DUBBING.md](docs/DUBBING.md) |
+| `client.text_to_speech.*` | Text-to-speech conversion | [TEXT_TO_SPEECH.md](docs/TEXT_TO_SPEECH.md) |
+| `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) |
+
+## Configuration Options
+
+### Configuration Precedence
+
+1. **Explicit parameters** (highest priority)
+2. **Settings.properties** (configured via initializer)
+3. **Environment variables** (lowest priority)
 
-Common target languages include:
-- `es` - Spanish
-- `pt` - Portuguese
-- `fr` - French
-- `de` - German
-- `it` - Italian
-- `pl` - Polish
-- `ja` - Japanese
-- `ko` - Korean
-- `zh` - Chinese
-- `hi` - Hindi
+### Environment Variables
+
+- `ELEVENLABS_API_KEY` - Your ElevenLabs API key (required)
+- `ELEVENLABS_BASE_URL` - API base URL (optional, defaults to `https://api.elevenlabs.io`)
+
+### Custom Environment Variable Names
+
+```ruby
+client = ElevenlabsClient.new(
+  api_key_env: "CUSTOM_API_KEY_VAR",
+  base_url_env: "CUSTOM_BASE_URL_VAR"
+)
+```
 
 ## Error Handling
 
-The client raises specific exceptions for different error conditions:
+The client provides specific exception types for different error conditions:
 
 ```ruby
 begin
-  client.create_dub(...)
-rescue ElevenlabsClient::AuthenticationError => e
-  puts "Invalid API key: #{e.message}"
-rescue ElevenlabsClient::RateLimitError => e
-  puts "Rate limit exceeded: #{e.message}"
+  result = client.text_to_speech.convert(voice_id, text)
+rescue ElevenlabsClient::AuthenticationError
+  puts "Invalid API key"
+rescue ElevenlabsClient::RateLimitError
+  puts "Rate limit exceeded"
 rescue ElevenlabsClient::ValidationError => e
-  puts "Validation error: #{e.message}"
+  puts "Invalid parameters: #{e.message}"
 rescue ElevenlabsClient::APIError => e
   puts "API error: #{e.message}"
 end
 ```
 
+### Exception Types
+
+- `AuthenticationError` - Invalid API key or authentication failure
+- `RateLimitError` - Rate limit exceeded
+- `ValidationError` - Invalid request parameters
+- `APIError` - General API errors
+
+## Rails Integration
+
+The gem is designed to work seamlessly with Rails applications. See the [examples](examples/) directory for complete controller implementations:
+
+- [DubsController](examples/dubs_controller.rb) - Complete dubbing workflow
+- [TextToSpeechController](examples/text_to_speech_controller.rb) - TTS with error handling
+- [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
+
 ## Development
 
-After checking out the repo, run `bundle install` to install dependencies.
+After checking out the repo, run:
+
+```bash
+bin/setup      # Install dependencies
+bundle exec rspec  # Run tests
+```
+
+To install this gem onto your local machine:
+
+```bash
+bundle exec rake install
+```
+
+To release a new version:
+
+1. Update the version number in `version.rb`
+2. Update `CHANGELOG.md`
+3. Run `bundle exec rake release`
+
+## Testing
+
+The gem includes comprehensive test coverage with RSpec:
+
+```bash
+# Run all tests
+bundle exec rspec
+
+# Run specific test files
+bundle exec rspec spec/elevenlabs_client/endpoints/
+bundle exec rspec spec/integration/
+
+# Run with documentation format
+bundle exec rspec --format documentation
+```
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub.
+Bug reports and pull requests are welcome on GitHub at https://github.com/yourusername/elevenlabs_client.
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request
 
 ## License
 
 The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md) for a detailed list of changes and version history.
+
+## Support
+
+- 📖 **Documentation**: [API Documentation](docs/)
+- 🐛 **Issues**: [GitHub Issues](https://github.com/yourusername/elevenlabs_client/issues)
+- 💬 **Discussions**: [GitHub Discussions](https://github.com/yourusername/elevenlabs_client/discussions)
+
+---
+
+Made with ❤️ for the Ruby community

data/lib/elevenlabs_client/client.rb

@@ -7,13 +7,17 @@ module ElevenlabsClient
   class Client
     DEFAULT_BASE_URL = "https://api.elevenlabs.io"
 
-    attr_reader :base_url, :api_key, :dubs
+    attr_reader :base_url, :api_key, :dubs, :text_to_speech, :text_to_speech_stream, :text_to_dialogue, :sound_generation
 
     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)
       @base_url = base_url || fetch_base_url(base_url_env)
       @conn = build_connection
       @dubs = Dubs.new(self)
+      @text_to_speech = TextToSpeech.new(self)
+      @text_to_speech_stream = TextToSpeechStream.new(self)
+      @text_to_dialogue = TextToDialogue.new(self)
+      @sound_generation = SoundGeneration.new(self)
     end
 
     # Makes an authenticated GET request
@@ -54,6 +58,62 @@ module ElevenlabsClient
       handle_response(response)
     end
 
+    # Makes an authenticated POST request expecting binary response
+    # @param path [String] API endpoint path
+    # @param body [Hash, nil] Request body
+    # @return [String] Binary response body
+    def post_binary(path, body = nil)
+      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
+      end
+
+      handle_binary_response(response)
+    end
+
+    # Makes an authenticated POST request with custom headers
+    # @param path [String] API endpoint path
+    # @param body [Hash, nil] Request body
+    # @param custom_headers [Hash] Additional headers
+    # @return [String] Response body (binary or text)
+    def post_with_custom_headers(path, body = nil, custom_headers = {})
+      response = @conn.post(path) do |req|
+        req.headers["xi-api-key"] = api_key
+        req.headers["Content-Type"] = "application/json"
+        custom_headers.each { |key, value| req.headers[key] = value }
+        req.body = body.to_json if body
+      end
+
+      # For streaming/binary responses, return raw body
+      if custom_headers["Accept"]&.include?("audio") || custom_headers["Transfer-Encoding"] == "chunked"
+        handle_binary_response(response)
+      else
+        handle_response(response)
+      end
+    end
+
+    # Makes an authenticated POST request with streaming response
+    # @param path [String] API endpoint path
+    # @param body [Hash, nil] Request body
+    # @param block [Proc] Block to handle each chunk
+    # @return [Faraday::Response] Response object
+    def post_streaming(path, body = nil, &block)
+      response = @conn.post(path) do |req|
+        req.headers["xi-api-key"] = api_key
+        req.headers["Content-Type"] = "application/json"
+        req.headers["Accept"] = "audio/mpeg"
+        req.body = body.to_json if body
+        
+        # Set up streaming callback
+        req.options.on_data = proc do |chunk, _|
+          block.call(chunk) if block_given?
+        end
+      end
+
+      handle_streaming_response(response)
+    end
+
     # Helper method to create Faraday::Multipart::FilePart
     # @param file_io [IO] File IO object
     # @param filename [String] Original filename
@@ -108,6 +168,36 @@ module ElevenlabsClient
       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
+
+    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}"
+      end
+    end
+
     def mime_for(filename)
       ext = File.extname(filename).downcase
       case ext

data/lib/elevenlabs_client/endpoints/sound_generation.rb

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class SoundGeneration
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/sound-generation
+    # Convert text to sound effects and retrieve audio (binary data)
+    # Documentation: https://elevenlabs.io/docs/api-reference/sound-generation
+    #
+    # @param text [String] Text prompt describing the sound effect
+    # @param options [Hash] Optional parameters
+    # @option options [Boolean] :loop Whether to create a looping sound effect (default: false)
+    # @option options [Float] :duration_seconds Duration in seconds (0.5 to 30, default: nil for auto-detection)
+    # @option options [Float] :prompt_influence Prompt influence (0.0 to 1.0, default: 0.3)
+    # @option options [String] :output_format Output format (e.g., "mp3_22050_32", default: "mp3_44100_128")
+    # @return [String] The binary audio data (usually an MP3)
+    def generate(text, **options)
+      endpoint = "/v1/sound-generation"
+      request_body = { text: text }
+
+      # Add optional parameters if provided
+      request_body[:loop] = options[:loop] unless options[:loop].nil?
+      request_body[:duration_seconds] = options[:duration_seconds] if options[:duration_seconds]
+      request_body[:prompt_influence] = options[:prompt_influence] if options[:prompt_influence]
+
+      # Handle output_format as query parameter
+      query_params = {}
+      query_params[:output_format] = options[:output_format] if options[:output_format]
+
+      # Build endpoint with query parameters if any
+      full_endpoint = query_params.any? ? "#{endpoint}?#{URI.encode_www_form(query_params)}" : endpoint
+
+      @client.post_binary(full_endpoint, request_body)
+    end
+
+    # Alias for backward compatibility and convenience
+    alias_method :sound_generation, :generate
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/text_to_dialogue.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class TextToDialogue
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/text-to-dialogue
+    # Converts a list of text and voice ID pairs into speech (dialogue) and returns audio.
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert
+    #
+    # @param inputs [Array<Hash>] A list of dialogue inputs, each containing text and a voice ID
+    # @option inputs [String] :text The text to be converted to speech
+    # @option inputs [String] :voice_id The voice ID to use for this text
+    # @param options [Hash] Optional parameters
+    # @option options [String] :model_id Identifier of the model to be used
+    # @option options [Hash] :settings Settings controlling the dialogue generation
+    # @option options [Integer] :seed Best effort to sample deterministically
+    # @return [String] The binary audio data (usually an MP3)
+    def convert(inputs, **options)
+      endpoint = "/v1/text-to-dialogue"
+      request_body = { inputs: inputs }
+
+      # Add optional parameters
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:settings] = options[:settings] if options[:settings] && !options[:settings].empty?
+      request_body[:seed] = options[:seed] if options[:seed]
+
+      @client.post_binary(endpoint, request_body)
+    end
+
+    # Alias for backward compatibility and convenience
+    alias_method :text_to_dialogue, :convert
+
+    private
+
+    attr_reader :client
+  end
+end

data/lib/elevenlabs_client/endpoints/text_to_speech.rb

@@ -0,0 +1,50 @@
+# frozen_string_literal: true
+
+module ElevenlabsClient
+  class TextToSpeech
+    def initialize(client)
+      @client = client
+    end
+
+    # POST /v1/text-to-speech/{voice_id}
+    # Convert text to speech and retrieve audio (binary data)
+    # Documentation: https://elevenlabs.io/docs/api-reference/text-to-speech/convert
+    #
+    # @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 (e.g. "eleven_monolingual_v1" or "eleven_multilingual_v1")
+    # @option options [Hash] :voice_settings Voice configuration (stability, similarity_boost, style, use_speaker_boost, etc.)
+    # @option options [Boolean] :optimize_streaming Whether to receive chunked streaming audio
+    # @return [String] The binary audio data (usually an MP3)
+    def convert(voice_id, text, **options)
+      endpoint = "/v1/text-to-speech/#{voice_id}"
+      request_body = { text: text }
+
+      # Add optional parameters
+      request_body[:model_id] = options[:model_id] if options[:model_id]
+      request_body[:voice_settings] = options[:voice_settings] if options[:voice_settings]
+
+      # Handle streaming optimization
+      if options[:optimize_streaming]
+        @client.post_with_custom_headers(endpoint, request_body, streaming_headers)
+      else
+        @client.post_binary(endpoint, request_body)
+      end
+    end
+
+    # Alias for backward compatibility and convenience
+    alias_method :text_to_speech, :convert
+
+    private
+
+    attr_reader :client
+
+    def streaming_headers
+      {
+        "Accept" => "audio/mpeg",
+        "Transfer-Encoding" => "chunked"
+      }
+    end
+  end
+end

data/lib/elevenlabs_client/endpoints/text_to_speech_stream.rb

@@ -0,0 +1,42 @@
+# 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
+    #
+    # @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/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ElevenlabsClient
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/lib/elevenlabs_client.rb

@@ -3,7 +3,11 @@
 require_relative "elevenlabs_client/version"
 require_relative "elevenlabs_client/errors"
 require_relative "elevenlabs_client/settings"
-require_relative "elevenlabs_client/dubs"
+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_dialogue"
+require_relative "elevenlabs_client/endpoints/sound_generation"
 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: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Vitor Oliveira
@@ -121,7 +121,11 @@ files:
 - README.md
 - lib/elevenlabs_client.rb
 - lib/elevenlabs_client/client.rb
-- lib/elevenlabs_client/dubs.rb
+- lib/elevenlabs_client/endpoints/dubs.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/errors.rb
 - lib/elevenlabs_client/settings.rb
 - lib/elevenlabs_client/version.rb