v0.8.9

v0.8.9 🐈 Happy Cat Day!

February 22 (2/22) is Cat Day in Japan — "2" sounds like "nyan" (meow) 🐱

🐈🐈🐈⬛⬛⬛🐈🐈🐈⬛🐈🐈🐈
⬛⬛🐈⬛⬛⬛⬛⬛🐈⬛⬛⬛🐈
🐈🐈🐈⬛⬛⬛🐈🐈🐈⬛🐈🐈🐈
🐈⬛⬛⬛⬛⬛🐈⬛⬛⬛🐈⬛⬛
🐈🐈🐈⬛🐈⬛🐈🐈🐈⬛🐈🐈🐈

• Add WebSocket API key auth and run script #261
• Include previously used tools in dynamic mode #262
• Add browser-based VRM demo with visual novel UI #263
• Add user_id session lookup and sessions endpoint #264
• Add hook to edit chat completion params #265
• Add API key support to example and download example UI #266
• Make user_id editable in websocket UI #267
• Add OpenClaw WebSocket example #268
• Enable cross-device access for OpenClaw example #269
• Update for v0.8.9 #270

Full Changelog: v0.8.8...v0.8.9

v0.8.8

What's Changed

• Add SileroStreamSpeechDetector with real-time speech segment recognition #254
• Invoke on_speech_detected on max_duration #255
• Add WebSocket-based streaming STT adapter with VAD support #256
• Allow multiple callbacks for VAD events #257
• Add 'voiced' VAD event #258
• Add STT WebSocket example (client + server) #259
• Update for v0.8.8🐙 #260

Full Changelog: v0.8.7...v0.8.8

v0.8.7

What's Changed

• Compile LANGUAGE_PATTERN for language parsing #247
• Add local gateway mode for SpeechGatewaySpeechSynthesizer #248
• Skip Kana conversion for non-Japanese text #249
• Add add_local_gateway method for easier TTS gateway setup #250
• Improve Admin Panel authentication and proxy support #251
• Unify default SQLite database filename to aiavatar.db #252
• Update for v0.8.7 #253

Full Changelog: v0.8.6...v0.8.7

v0.8.6

What's Changed

• Add admin panel for monitoring, control, and evaluation #230
• Add user create and delete functionality to admin panel #231
• Add AdminPanel for dynamic adapter registration #232
• Fix preroll buffer size calculation for accurate audio capture #233
• Add final chunk to the response from control/perform API #234
• Add pcm_to_wave conversion method #235
• Include dynamic config fields for Admin Panel #236
• Add error tracking to performance records and Admin Panel #237
• Add Processing phase metrics and detailed tool call logging #238
• Display tool call status in websocket UI #239
• Fix SQLite metrics query for short time periods #240
• Add configurable dummy components for STT/LLM/TTS #241
• Add validate_request hook for filtering requests #242
• Add early text validation for AzureStreamSpeechDetector #243
• Add per-session speech speed control for personalized user experience #244
• Fix voice_text returning None when wakeword is not matched #245
• Update for v0.8.6 #246

Full Changelog: v0.8.5...v0.8.6

v0.8.5

What's Changed

• Add centralized PostgreSQL pool provider and integration #217
• Refactor CharacterService and add SQLite support #218
• Add user management support to character module #219
• Add callback hooks and local server adapter #220
• Refactor local client to use AIAvatarLocalServer #221
• Add bind_character for simplified character integration #222
• Fix response stopping logic based on awake state #223
• Fix empty system prompt being added to messages #224
• Add on_error handler for LLM API error responses #225
• Add Azure OpenAI client support in CharacterService #226
• Log speech synthesis only in debug mode #227
• Add customizable chat print hook to LLM base class #228
• Update for v0.8.5 #229

Full Changelog: v0.8.4...v0.8.5

v0.8.4

What's Changed

• Add follow_redirects option to SpeechSynthesizer #210
• Add MotionPNGTuber example #211
• Add kana_map caching to AlphabetToKanaPreprocessor #212
• Add GetDiaryTool for retrieving diary and schedule #213
• Add batch activity range generation to service #214
• Add block_barge_in to prevent interruption during critical responses #215
• Update for v0.8.4 #216

Full Changelog: v0.8.3...v0.8.4

v0.8.3

What's Changed

• Refactor system prompt handling to support async functions #203
• Fix tool call result handling in MCPBase #204
• Add async lock to Postgres pool initialization #205
• Add character management feature #206
• Add MemorySearchTool and update memory client usage #207
• Add AudioConverter and async response parsing to TTS #208
• Update for v0.8.3 #209

Full Changelog: v0.8.2...v0.8.3

v0.8.2

What's Changed

• Add invoke queue support for sequential request handling #201
• Update for v0.8.2🗻🦅🍆 #202

Full Changelog: v0.8.1...v0.8.2

v0.8.1

What's Changed

• Remove Silero VAD dependency from AzureStreamSpeechDetector #194
• Add allow_merge flag to request handling pipeline #195
• Add camera integration and UI enhancements to WebSocket demo #196
• Remove pgvector dependency and handle vector conversion manually #197
• Add built-in language tag parsing in pipeline #198
• Improve control tag handling in response splitting #199
• 🥳 New year update for v0.8.1 🎍 #200

Full Changelog: v0.8.0...v0.8.1

v0.8.0

What's Changed

• Add README for WebSocket example #183
• Stop AI speech immediately when user starts speaking🎄🎁 #185
• Add AzureStreamSpeechDetector with STT #186
• Refactor SileroSpeechDetector and improve tests #187
• Refactor PostgreSQL adapters to use asyncpg #188
• Notify client on request acceptance in pipeline #189
• Add on_speech_detecting callback to AzureStreamSpeechDetector #190
• Refactor microphone mute logic and response handling #191
• Set SileroSpeechDetector as the default VAD #192
• Update for v0.8.0 #193

Full Changelog: v0.7.21...v0.8.0