14 Commits

Author SHA1 Message Date
d1ec42fa51
big ass formatting 2025-06-05 21:31:06 -06:00
99bd17008e
feat: Uncomment model parameter for speech recognition to improve voice chat handling 2025-05-30 23:01:10 -06:00
445be20991
feat: Integrate Google Cloud Speech-to-Text for voice transcription and enhance response handling 2025-05-30 22:49:22 -06:00
36f3f80487
feat: Implement dedicated voice text channel functionality and logging for voice interactions 2025-05-30 22:34:27 -06:00
1197a345b9
fix: Remove unnecessary FFMPEG_OPTIONS for local file handling in VoiceGatewayCog 2025-05-30 22:25:10 -06:00
1c5db9f9e9
fix: Use functools.partial for transcribing audio with Whisper model in VoiceGatewayCog 2025-05-30 22:13:04 -06:00
7dd00644a2
fix: Update asyncio task creation to use bot loop in VoiceAudioSink for audio segment processing 2025-05-30 22:11:41 -06:00
429d416010
fix: Update VoiceAudioSink write method to accept VoiceData and extract PCM data 2025-05-30 22:08:49 -06:00
2706abe5f6
refactor: Simplify VoiceAudioSink initialization by removing voice_client parameter 2025-05-30 22:07:42 -06:00
09a9ced39c
feat: Add wants_opus method to VoiceAudioSink to indicate PCM audio processing 2025-05-30 22:06:04 -06:00
3824ba9a6c
feat: Refactor audio processing in VoiceGatewayCog to remove OpusDecoder and integrate FFmpeg for audio conversion 2025-05-30 22:01:36 -06:00
c0c65fe3d1
fix: Remove unused imports from opuslib in VoiceGatewayCog 2025-05-30 21:42:50 -06:00
743dd21860
fix: Add traceback import for detailed error reporting on opuslib import failure 2025-05-30 21:41:41 -06:00
db64d0e790
feat: Add Google Cloud TTS provider
Introduces a new TTS provider using Google Cloud Text-to-Speech (Chirp HD model). This allows for higher quality and more natural-sounding voice synthesis.

The `TTSProviderCog` now includes:
- A `google_cloud_tts` option in the `_synthesize_speech` method.
- Checks for the `google-cloud-texttospeech` library and provides installation instructions if missing.
- Error handling for common Google Cloud TTS issues like quota limits or credential problems.
- A new choice in the `/ttsprovider` slash command for "Google Cloud TTS (Chirp HD)".
- A check for the availability of the `google.cloud.texttospeech` module on startup.
2025-05-30 21:25:01 -06:00