audio 252 tts 242 voice 182 python 158 text-to-speech 124 asr 108 ai 96 speech-recognition 90 pytorch 88 nlp 75 whisper 70 speech-to-text 70 deep-learning 65 llm 64 stt 63 machine-learning 62 transcription 56 recognition 42 speech-synthesis 42 vad 42 learning 39 tensorflow 37 text 37 NLP 36 transformer 35 language 32 onnx 31 phonetics 31 natural-language-processing 30 vision 30 deep 29 openai 27 real-time 27 agent 27 voice-activity-detection 27 mcp 26 cli 26 synthesis 25 voice-cloning 25 music 25 speech-processing 25 realtime 24 grpc 23 AI 23 BERT 23 GPT-2 23 audio-processing 22 Wav2Vec2 22 ViT 22 agents 21 search 21 diarization 20 livekit 20 linguistics 19 jax 19 plugin 19 hacktoberfest 18 streaming 18 avatar 17 voice-ai 17 memory 17 pretrained-models 17 evaluation 17 visual 16 omni 16 reflection 16 rtc 16 sdk 16 virtual-character 16 praat 16 signal-processing 16 speech-enhancement 16 video 16 kokoro 15 api 15 qwen 15 text to speech 15 mlx 14 wake-word 14 alignment 14 machine learning 14 to 14 vlm 14 forced-alignment 13 pronunciation 13 speech synthesis 13 ASR 13 dictation 13 inference 13 offline 13 pipecat 13 model-hub 13 glm 13 pytorch-transformers 13 gemma 12 deepseek 12 machine 12 vocoder 12 assistant 12 prosody 12