aiavatarkit

What's Changed

• Add experimental support for OpenAI audio APIs by @uezo in https://github.com/uezo/aiavatarkit/pull/48
• Correct decibel calculation to handle silence in microphone input by @uezo in https://github.com/uezo/aiavatarkit/pull/49
• Add new endpoints to ChatProcessor and SpeechController by @uezo in https://github.com/uezo/aiavatarkit/pull/50
• Add experimental support for vision input to ChatGPT by @uezo in https://github.com/uezo/aiavatarkit/pull/51

Full Changelog: https://github.com/uezo/aiavatarkit/compare/0.5.5...0.5.6

What's Changed

• Add sample rate configuration for audio devices by @uezo in https://github.com/uezo/aiavatarkit/pull/47

Full Changelog: https://github.com/uezo/aiavatarkit/compare/0.5.4...0.5.5

What's Changed

• Add experimental support for LM Studio API by @uezo in https://github.com/uezo/aiavatarkit/pull/46

Full Changelog: https://github.com/uezo/aiavatarkit/compare/0.5.3...0.5.4

What's Changed

• Improve speech recognition accuracy by @uezo in https://github.com/uezo/aiavatarkit/pull/44
• Add API for checking AI avatar status by @uezo in https://github.com/uezo/aiavatarkit/pull/45

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.5.2...0.5.3

What's Changed

• Enable external control of WakewordListener by @uezo in https://github.com/uezo/aiavatarkit/pull/38
• Add REST API for controlling listener, avatar, and logging by @uezo in https://github.com/uezo/aiavatarkit/pull/39
• Fix AzureWakewordListener network reconnection issue #40 by @uezo in https://github.com/uezo/aiavatarkit/pull/41
• Add support Claude and Gemini by @uezo in https://github.com/uezo/aiavatarkit/pull/42
• Set subprocess-based audio playback as default by @uezo in https://github.com/uezo/aiavatarkit/pull/43

Full Changelog: https://github.com/uezo/aiavatarkit/compare/0.5.0...v0.5.2

What's Changed

• Simplify AIAvatar initialization and enhance customization https://github.com/uezo/aiavatarkit/pull/35
• Fix speech subprocess https://github.com/uezo/aiavatarkit/pull/36
• Merge subprocess support into VoicevoxSpeechController https://github.com/uezo/aiavatarkit/pull/37

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.4.5...0.5.0

What's Changed

• Add experimental SpeechController to handle speech in separate process to reduce the noise https://github.com/uezo/aiavatarkit/pull/33
• Add support for Azure Text-to-Speech (Experimental) https://github.com/uezo/aiavatarkit/pull/34

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.4.4...v0.4.5

What's Changed

• Add support for animation in VRChat https://github.com/uezo/aiavatarkit/pull/25
• Add feature to reset histories after timeout https://github.com/uezo/aiavatarkit/pull/28
• Disable wake word detection during conversations https://github.com/uezo/aiavatarkit/pull/29
• Make it possible to exit chat on turn end https://github.com/uezo/aiavatarkit/pull/30
• Ignore non-verbal sounds on voice recognition https://github.com/uezo/aiavatarkit/pull/31
• Fix bug where responses from ChatGPT without punctuation marks '。', '、', '！' or '？' are ignored https://github.com/uezo/aiavatarkit/pull/32

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.4.0...v0.4.4

What's Changed

• Make it easier to change AI model by @uezo in https://github.com/uezo/aiavatarkit/pull/21
• Prevent voice playback from blocking thread by @uezo in https://github.com/uezo/aiavatarkit/pull/22
• Reduce noise in voice by @uezo in https://github.com/uezo/aiavatarkit/pull/23
• Support Azure Speech Services by @uezo in https://github.com/uezo/aiavatarkit/pull/24

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.3.1...v0.4.0

What's Changed

• Support custom action on start processing chat and listening voice by @uezo in https://github.com/uezo/aiavatarkit/pull/19
• Update OpenAI client library to 1.12.0 by @uezo in https://github.com/uezo/aiavatarkit/pull/20

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.2.1...v0.3.1

What's Changed

• Fix bug that audio device settings are ignored 😔 in https://github.com/uezo/aiavatarkit/pull/17

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.2.0...v0.2.1

What's Changed

• Change audio library from PyAudio to sounddevice in https://github.com/uezo/aiavatarkit/pull/14
• Fix bug that the value for channels is invalid in https://github.com/uezo/aiavatarkit/pull/15
• Add support for Function Calling⚡️ in https://github.com/uezo/aiavatarkit/pull/16

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.1.4...v0.2.0

What's Changed

• Make it possible to reset face after speech #9 by @uezo in https://github.com/uezo/aiavatarkit/pull/11
• Add volume_threshold as an argument for AIAvatar #10 by @uezo in https://github.com/uezo/aiavatarkit/pull/12

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.1.3...v0.1.4

What's Changed

• Support face expression in VRChat🥰 by @uezo in https://github.com/uezo/aiavatarkit/pull/7
• Support start chatting on wake by @uezo in https://github.com/uezo/aiavatarkit/pull/8

Full Changelog: https://github.com/uezo/aiavatarkit/compare/v0.1.2...v0.1.3

Mainly improve procedure for configuring audio devices.

• Support getting audio device by name #3
• Support interactive audio device selection #4
• Use shared PyAudio instance in each recording #5
• Add verbose mode to WakewordListener #6