Version 1.0.20:

- Added: View My Voices and View Voice Library buttons to Select Voice panel.

- Improved: Branching Dialogue panel now lets you specify a number of variants to generate for each entry.

- Changed: Renamed ElevenLabs script folder to Voices.

- Fixed: Saving asset files issue when saving to root Assets folder.

Version 1.0.19:

- Updated optional assembly definitions package to work with Dialogue System assembly definitions.

Version 1.0.18:

- Handles new format **ActorName:** returned by OpenAI.

Version 1.0.17:

- Improved: Disambiguates namespaces from other third party OpenAI-Unity packages.

Version 1.0.16:

- Improved: Now supports and defaults to GPT-4o-mini.

- Improved: Assistant Window lets you choose any chat model and defaults to GPT-4o-mini.

Version 1.0.15:

- Added: OpenAI text to speech generation.

- Added: Branching dialogue text generator. (Dialogue Smith replacement.)

- Improved: Different base URL can now be set for editor time use, too.

- DeepVoice: Added integration.

- ElevenLabs: Added Multilingual1 and Multilingual2 options.

Version 1.0.14:

- Improved: Now supports and defaults to GPT-4o.

- Improved: Localized field's AI button is now dropdown to select Translate or Generate Voiceover.

- Fixed: Method call in AITextUtility made back compatible with Unity 2019 and 2020.

Version 1.0.13:

- Improved: Can now assign custom value to OpenAI.BaseURL to use different services (e.g., Azure).

- Improved: Removed English-specific assumptions about handling of colons (:) inside generated text, other improvements.

- ElevenLabs: Addon now remembers last folder audio file was saved in for easier selection.

Version 1.0.12:

- Improved: Handling of colons (:) inside generated text response when generating conversations.

Version 1.0.11:

- Added: Support for fine-tuned models.

- Improved: Freeform runtime conversation now ends automatically with goodbye line when max tokens are reached.

- Improved: Now handles more varied dialogue response formats.

- Dialogue Smith: Removed. Dialogue Smith has discontinued service.

Version 1.0.10:

- Added: Text Table asset translation.

- Improved: RuntimeAIConversation.ApproximateTokenCount and ApproachedMaxTokens are now settable.

- Improved: RuntimeAIConversation handles additional text formats for dialogue replies from OpenAI.

- Improved: Runtime dialogue now gets field info from Lua so you can change it at runtime.

- Changed: Translation panels now default to GPT-3.5 Turbo 16K (since Curie is deprecated).

- Fixed: Can now tick Welcome Window's Show On Start checkbox even if no OpenAI key is set.

- Fixed: Dialogue Smith now keeps existing text if present.

- Overtone: Added integration.

Version 1.0.9.1:

- Fixed: Can build for WebGL again. (WebGL doesn't currently support Microphone.)

Version 1.0.9:

- Improved: Runtime dialogue now gets field info from Lua so you can change it at runtime.

- Overtone: Added integration.

Version 1.0.8.1:

- Fixed: ElevenLabs voice selection dropdown wasn't showing custom voices.

Version 1.0.8:

- Added: Support for GPT-4 Turbo (model currently in preview).

- Added: Support for ElevenLabs v2 models.

- Improved: Added top_p, frequency_penalty, and presence_penalty to editor windows, runtime settings, and API.

- Improved: Generate Voice section can now add sequencer command, remembers last folder audio files were saved into.

- Improved: Select Voice section now has button to generate all voice lines for an actor.

Version 1.0.7:

- Fixed: Runtime dialogue strips "<speaker> says:" from text if present.

- Improved: Actor and location descriptions are now parsed for [var] and [lua] tags in runtime generation.

Version 1.0.6:

- Added ChatGPT-like AI Assistant Window.

- Added backward compatibility with Unity 2020.

- Fixed issue in case where Dialogue Smith returns no text for a dialogue entry.

Older release notes are in asset's _RELEASE_NOTES.txt file.

Dialogue System for Unity Addon for OpenAI, ElevenLabs & Other Generative AI