Add TTS support

.github/workflows/cicd.yml

@@ -35,16 +35,20 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['3.1', '3.2', '3.3', '3.4', 'jruby-10.0.1.0']
-        rails-version: ['rails-7.1', 'rails-7.2', 'rails-8.0']
+        ruby-version: ['3.1', '3.2', '3.3', '3.4', 'jruby-10.0.2.0']
+        rails-version: ['rails-7.1', 'rails-7.2', 'rails-8.0', 'rails-8.1']
         exclude:
           # Rails 8 requires Ruby 3.2+
           - ruby-version: '3.1'
             rails-version: 'rails-8.0'
+          - ruby-version: '3.1'
+            rails-version: 'rails-8.1'
           # JRuby only supports up to 7.1 right now
-          - ruby-version: 'jruby-10.0.1.0'
+          - ruby-version: 'jruby-10.0.2.0'
+            rails-version: 'rails-8.1'
+          - ruby-version: 'jruby-10.0.2.0'
             rails-version: 'rails-8.0'
-          - ruby-version: 'jruby-10.0.1.0'
+          - ruby-version: 'jruby-10.0.2.0'
             rails-version: 'rails-7.2'
 
     steps:
@@ -200,4 +204,4 @@ jobs:
           fi
         }
       env:
-        GEM_HOST_API_KEY: "${{secrets.RUBYGEMS_AUTH_TOKEN}}"
+        GEM_HOST_API_KEY: "${{secrets.RUBYGEMS_AUTH_TOKEN}}"

.gitignore

@@ -48,6 +48,7 @@ build-iPhoneSimulator/
 # for a library or gem, you might want to ignore these files since the code is
 # intended to run in multiple environments; otherwise, check them in:
 Gemfile.lock
+gemfiles/*.lock
 # .ruby-version
 # .ruby-gemset
 

Appraisals

@@ -17,3 +17,9 @@ appraise 'rails-8.0' do
     gem 'rails', '~> 8.0.0'
   end
 end
+
+appraise 'rails-8.1' do
+  group :development do
+    gem 'rails', '~> 8.1.0'
+  end
+end

README.md

@@ -74,6 +74,11 @@ RubyLLM.embed "Ruby is elegant and expressive"
 RubyLLM.transcribe "meeting.wav"
 ```
 
+```ruby
+# Text to speech
+RubyLLM.tts "Hello, welcome to RubyLLM!"
+```
+
 ```ruby
 # Moderate content for safety
 RubyLLM.moderate "Check if this text is safe"

docs/_core_features/text-to-speech.md

@@ -0,0 +1,96 @@
+---
+layout: default
+title: Text to Speech
+nav_order: 7
+description: Convert text to speech
+redirect_from:
+  - /guides/audio-transcription
+  - /guides/transcription
+---
+
+# {{ page.title }}
+{: .d-inline-block .no_toc }
+
+v1.9.0+
+{: .label .label-green }
+
+{{ page.description }}
+{: .fs-6 .fw-300 }
+
+## Table of contents
+{: .no_toc .text-delta }
+
+1. TOC
+{:toc}
+
+---
+
+After reading this guide, you will know:
+
+*   How to generate speech from text.
+*   How to save audio files.
+*   How to select different voices.
+*   How to access raw audio data.
+*   Specifics of language support.
+
+## Basic Text to Speech
+
+Generate audio with the global `RubyLLM.tts` method:
+
+```ruby
+audio = RubyLLM.tts("Hello, welcome to RubyLLM!")
+
+```
+
+## Save Audio File
+You can save the generated audio to a file.
+If you are using OpenAI, the audio will be saved as an MP3 file.
+
+```ruby
+audio = RubyLLM.tts("This is a text to speech example.", provider: :openai, model: "gpt-4o-mini-tts")
+audio.save("example.mp3")
+```
+
+If you are using Gemini, the audio will be saved as a raw PCM file.
+
+```ruby
+audio = RubyLLM.tts("This is a text to speech example.", provider: :gemini, model: "gemini-2.5-flash-preview-tts")
+audio.save("example.pcm")
+```
+
+You can convert it to MP3 using ffmpeg:
+
+```bash
+ffmpeg -f s16le -ar 24000 -ac 1 -i example.pcm example.mp3
+```
+
+### Select Voice
+You can specify different voices. Supported voices for OpenAI
+are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, and verse.
+
+For Gemini have a look at the [gemini voices](https://ai.google.dev/gemini-api/docs/speech-generation#voices).
+
+```ruby
+# Using a specific voice
+voice = "ash"
+audio = RubyLLM.tts("Hello, this is a #{voice}`s voice.", voice: voice)
+```
+
+### Access Audio Data
+You can access the raw audio data:
+
+```ruby
+audio = RubyLLM.tts("Accessing raw audio data.")
+audio.data # => binary audio data (MP3 for OpenAI, PCM for Gemini)
+```
+
+### Language Support
+OpenAi and Gemini gather language support automatically based on the text provided.
+Previously, you could specify the language manually in Gemini.
+
+## Next Steps
+
+*   [Chatting with AI Models]({% link _core_features/chat.md %}): Learn about conversational AI.
+*   [Image Generation]({% link _core_features/image-generation.md %}): Generate images from text.
+*   [Error Handling]({% link _advanced/error-handling.md %}): Master handling API errors.
+

docs/index.md

@@ -138,6 +138,11 @@ RubyLLM.embed "Ruby is elegant and expressive"
 RubyLLM.transcribe "meeting.wav"
 ```
 
+```ruby
+# Text to speech
+RubyLLM.tts "Hello, welcome to RubyLLM!"
+```
+
 ```ruby
 # Moderate content for safety
 RubyLLM.moderate "Check if this text is safe"