eleven_rb 0.4.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fa71eff851a0c6b80f139e801962bceaf1bb371f6e9a0cd325c47b2ee6f4994c
-  data.tar.gz: aa640970faba75afe3cbacdc16958ee63c1f2ecfb009512cd9e8182117e16d29
+  metadata.gz: ed711abcce18771ad13f10bcb29754605be61f7d02f7114f0e0b28b0dad4d556
+  data.tar.gz: 146285726bc80b0c3eab0b307a7ec4b788a8f3465903992bb12fc2b34bc1694b
 SHA512:
-  metadata.gz: a537ba9de014afc366c348a71613f257b6380ae784979fb42cd55522610c85661e0e34907c770642fa268051cbb91b24110e00d5e8b7305d5c913a81e04705a6
-  data.tar.gz: c1f4e236fb327b737b4e6346bf3a71bfec357d4f7f09a0e1eaf9c8889ef2251ff40b8eeb3be959e98b58e2a76ff6305e7391d64f0c33a9ce1fb38897b958f1fa
+  metadata.gz: 6bf8e216c83287bb099e4a6bbed4ef718329f361fb7dfb4c70bf122f2512c74916eb1540fe6a1dfd4ae01e0edc53edc05408a017946f504c09611a54a6c2370b
+  data.tar.gz: 1839c52e3adf4efed58c410f08fa5c5e4818fde0964922e0752019b6606d726ed66a4f48a767b4e2110aa3b0cf98e7f4666eaef64552ec9f0f976378b1ef5094

data/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.0.0] - 2026-03-10
+
+### Added
+
+- Text-to-Dialogue multi-speaker audio generation via `client.text_to_dialogue.generate` (`POST /v1/text-to-dialogue`)
+- `Client#text_to_dialogue` resource with `dialogue` alias
+- Multi-speaker input validation (max 10 unique voices, 5000 character limit)
+- `eleven_v3` model added to `CostInfo::COST_PER_1K_CHARS` ($0.30/1K chars)
+- `Models#latest` method returning the most capable model (`eleven_v3`)
+- Audio tags support via v3 model (`[laughs]`, `[whispers]`, `[excited]`, etc.)
+- `CostInfo` now accepts `character_count:` keyword as alternative to `text:`
+- TTS generation with word-level timestamps via `client.tts.generate_with_timestamps`
+
+### Changed
+
+- `CostInfo#initialize` signature: `text:` is now optional when `character_count:` is provided (backwards-compatible)
+
 ## [0.4.0] - 2026-03-10
 
 ### Added

data/README.md

@@ -4,12 +4,13 @@
 [![CI](https://github.com/webventures/eleven_rb/actions/workflows/ci.yml/badge.svg)](https://github.com/webventures/eleven_rb/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-A Ruby client for the [ElevenLabs](https://try.elevenlabs.io/qyk2j8gumrjz) Text-to-Speech, Speech-to-Speech, Sound Effects, and Music API.
+A Ruby client for the [ElevenLabs](https://try.elevenlabs.io/qyk2j8gumrjz) Text-to-Speech, Speech-to-Speech, Text-to-Dialogue, Sound Effects, and Music API.
 
 ## Features
 
 - Text-to-Speech generation and streaming
 - Speech-to-Speech voice conversion
+- Text-to-Dialogue multi-speaker generation with audio tags
 - Sound effects generation from text descriptions
 - Music generation from prompts or composition plans
 - Voice management (list, get, create, update, delete)
@@ -73,7 +74,7 @@ audio.save_to_file("output.mp3")
 audio = client.tts.generate(
   "Hello world",
   voice_id: "voice_id",
-  model_id: "eleven_multilingual_v2",
+  model_id: "eleven_v3",             # Most expressive, 70+ languages, audio tags
   voice_settings: {
     stability: 0.5,
     similarity_boost: 0.75
@@ -111,6 +112,42 @@ io = File.open("input.mp3", "rb")
 audio = client.sts.convert(io, voice_id: "voice_id")
 ```
 
+### Text-to-Dialogue
+
+```ruby
+# Generate multi-speaker dialogue
+audio = client.text_to_dialogue.generate([
+  { text: "[excited] Welcome to the show!", voice_id: "voice_abc" },
+  { text: "[laughs] Thanks for having me.", voice_id: "voice_xyz" },
+  { text: "So tell us about your project...", voice_id: "voice_abc" }
+])
+audio.save_to_file("dialogue.mp3")
+
+# With options
+audio = client.dialogue.generate(
+  inputs,
+  model_id: "eleven_v3",
+  language_code: "en",
+  settings: { stability: 0.5 },
+  seed: 42,
+  output_format: "mp3_44100_192"
+)
+```
+
+### Audio Tags
+
+The `eleven_v3` model supports inline audio tags for expressive speech:
+
+```ruby
+audio = client.tts.generate(
+  "[excited] Oh wow, this is AMAZING! [laughs] I can't believe it...",
+  voice_id: "voice_id",
+  model_id: "eleven_v3"
+)
+```
+
+Supported tags include `[laughs]`, `[whispers]`, `[sighs]`, `[excited]`, `[sarcastic]`, `[curious]`, `[pause]`, and more. Use CAPS for emphasis, `...` for pauses, and `—` for interruptions. See the [ElevenLabs v3 documentation](https://elevenlabs.io/docs/guides/audio-tags) for the full list.
+
 ### Sound Effects
 
 ```ruby
@@ -274,6 +311,9 @@ client = ElevenRb::Client.new(
 models = client.models.list
 models.each { |m| puts "#{m.name} (#{m.model_id})" }
 
+# Get the latest/most capable model
+client.models.latest  # => "eleven_v3"
+
 # Get multilingual models
 client.models.multilingual
 

data/lib/eleven_rb/client.rb

@@ -101,6 +101,14 @@ module ElevenRb
       @music ||= Resources::Music.new(http_client)
     end
 
+    # Text-to-dialogue resource
+    #
+    # @return [Resources::TextToDialogue]
+    def text_to_dialogue
+      @text_to_dialogue ||= Resources::TextToDialogue.new(http_client)
+    end
+    alias dialogue text_to_dialogue
+
     # Voice slot manager
     #
     # @return [VoiceSlotManager]

data/lib/eleven_rb/objects/cost_info.rb

@@ -12,6 +12,7 @@ module ElevenRb
         'eleven_monolingual_v1' => 0.30,
         'eleven_multilingual_v1' => 0.30,
         'eleven_multilingual_v2' => 0.30,
+        'eleven_v3' => 0.30,
         'eleven_turbo_v2' => 0.18,
         'eleven_turbo_v2_5' => 0.18,
         'eleven_english_sts_v2' => 0.30,
@@ -23,11 +24,12 @@ module ElevenRb
 
       # Initialize cost info
       #
-      # @param text [String] the text being converted
+      # @param text [String, nil] the text being converted
+      # @param character_count [Integer, nil] direct character count (alternative to text)
       # @param voice_id [String] the voice ID
       # @param model_id [String] the model ID
-      def initialize(text:, voice_id:, model_id:)
-        @character_count = text.length
+      def initialize(voice_id:, model_id:, text: nil, character_count: nil)
+        @character_count = character_count || text&.length || 0
         @voice_id = voice_id
         @model_id = model_id
       end

data/lib/eleven_rb/resources/models.rb

@@ -54,6 +54,13 @@ module ElevenRb
         get('eleven_multilingual_v2') || tts_capable.first
       end
 
+      # Get the latest/most capable model
+      #
+      # @return [Objects::Model, nil]
+      def latest
+        get('eleven_v3') || default
+      end
+
       # Get model IDs as array
       #
       # @return [Array<String>]

data/lib/eleven_rb/resources/text_to_dialogue.rb

@@ -0,0 +1,113 @@
+# frozen_string_literal: true
+
+module ElevenRb
+  module Resources
+    # Text-to-dialogue resource for multi-speaker audio generation
+    #
+    # @example Generate dialogue
+    #   audio = client.text_to_dialogue.generate([
+    #     { text: "[excited] Welcome!", voice_id: "voice_abc" },
+    #     { text: "[laughs] Thanks!", voice_id: "voice_xyz" }
+    #   ])
+    #   audio.save_to_file("dialogue.mp3")
+    class TextToDialogue < Base
+      DEFAULT_MODEL = 'eleven_v3'
+      MAX_VOICES_PER_REQUEST = 10
+      MAX_TEXT_LENGTH = 5000
+
+      # Generate dialogue audio from multiple speaker inputs
+      #
+      # @param inputs [Array<Hash>] Array of { text:, voice_id: } hashes
+      # @param model_id [String] Model to use (only eleven_v3 supported)
+      # @param language_code [String, nil] ISO 639-1 language code
+      # @param settings [Hash, nil] Generation settings (stability: 0.0-1.0)
+      # @param seed [Integer, nil] Seed for reproducibility
+      # @param output_format [String] Audio output format
+      # @param apply_text_normalization [String] "auto", "on", or "off"
+      # @return [Objects::Audio]
+      def generate(
+        inputs,
+        model_id: DEFAULT_MODEL,
+        language_code: nil,
+        settings: nil,
+        seed: nil,
+        output_format: 'mp3_44100_128',
+        apply_text_normalization: 'auto'
+      )
+        validate_inputs!(inputs)
+
+        body = build_request_body(inputs, model_id, language_code, settings, seed,
+                                  apply_text_normalization)
+
+        response = post_binary(
+          "/text-to-dialogue?output_format=#{output_format}",
+          body
+        )
+
+        build_audio_response(response, inputs, output_format, model_id)
+      end
+
+      private
+
+      def build_request_body(inputs, model_id, language_code, settings, seed,
+                             apply_text_normalization)
+        body = {
+          inputs: inputs.map { |i| { text: i[:text], voice_id: i[:voice_id] } },
+          model_id: model_id,
+          apply_text_normalization: apply_text_normalization
+        }
+
+        body[:language_code] = language_code if language_code
+        body[:settings] = settings if settings
+        body[:seed] = seed if seed
+        body
+      end
+
+      def build_audio_response(response, inputs, output_format, model_id)
+        total_text = inputs.map { |i| i[:text] }.join("\n")
+        total_chars = inputs.sum { |i| i[:text].length }
+        primary_voice = inputs.first[:voice_id]
+
+        audio = Objects::Audio.new(
+          data: response, format: output_format,
+          voice_id: primary_voice, text: total_text, model_id: model_id
+        )
+
+        cost_info = Objects::CostInfo.new(
+          character_count: total_chars, voice_id: primary_voice, model_id: model_id
+        )
+
+        http_client.config.trigger(
+          :on_audio_generated,
+          audio: audio, voice_id: primary_voice,
+          text: total_text, cost_info: cost_info.to_h
+        )
+
+        audio
+      end
+
+      def validate_inputs!(inputs)
+        raise Errors::ValidationError, 'inputs must be a non-empty array' unless inputs.is_a?(Array) && !inputs.empty?
+
+        inputs.each_with_index do |input, i|
+          validate_presence!(input[:text], "inputs[#{i}].text")
+          validate_presence!(input[:voice_id], "inputs[#{i}].voice_id")
+        end
+
+        unique_voices = inputs.map { |i| i[:voice_id] }.uniq
+        if unique_voices.length > MAX_VOICES_PER_REQUEST
+          raise Errors::ValidationError,
+                "Maximum #{MAX_VOICES_PER_REQUEST} unique voices per request " \
+                "(got #{unique_voices.length})"
+        end
+
+        total_chars = inputs.sum { |i| i[:text].length }
+        return unless total_chars > MAX_TEXT_LENGTH
+
+        raise Errors::ValidationError,
+              "Total text length #{total_chars} exceeds maximum " \
+              "#{MAX_TEXT_LENGTH} characters"
+      end
+    end
+  end
+end

data/lib/eleven_rb/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ElevenRb
-  VERSION = '0.4.0'
+  VERSION = '1.0.0'
 end

data/lib/eleven_rb.rb

@@ -109,6 +109,7 @@ require_relative 'eleven_rb/resources/user'
 require_relative 'eleven_rb/resources/sound_effects'
 require_relative 'eleven_rb/resources/music'
 require_relative 'eleven_rb/resources/speech_to_speech'
+require_relative 'eleven_rb/resources/text_to_dialogue'
 
 # High-level components
 require_relative 'eleven_rb/voice_slot_manager'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: eleven_rb
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Web Ventures Ltd
@@ -122,9 +122,9 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.9'
 description: |
-  A well-structured Ruby gem for ElevenLabs TTS with voice library management,
-  streaming support, voice slot optimization, and comprehensive callbacks for
-  logging, error tracking, and cost monitoring.
+  A comprehensive Ruby client for ElevenLabs covering Text-to-Speech,
+  Speech-to-Speech, Text-to-Dialogue, Sound Effects, and Music generation
+  with voice management, streaming, and built-in cost tracking.
 email:
 - gems@dev.webven.nz
 executables: []
@@ -158,6 +158,7 @@ files:
 - lib/eleven_rb/resources/music.rb
 - lib/eleven_rb/resources/sound_effects.rb
 - lib/eleven_rb/resources/speech_to_speech.rb
+- lib/eleven_rb/resources/text_to_dialogue.rb
 - lib/eleven_rb/resources/text_to_speech.rb
 - lib/eleven_rb/resources/user.rb
 - lib/eleven_rb/resources/voice_library.rb
@@ -189,5 +190,5 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 rubygems_version: 3.6.9
 specification_version: 4
-summary: Ruby client for the ElevenLabs Text-to-Speech API
+summary: Ruby client for the ElevenLabs Audio AI API
 test_files: []