Running on A10G Featured 120 faster-qwen3-tts π 120 Generate spoken audio from text with custom or cloned voices
Running on L4 Featured 723 StyleTTS 2 π£ 723 Efficient, fast, and natural text to speech with StyleTTS 2!
mrfakename/styletts2-detector-turbo Audio Classification β’ 0.6B β’ Updated Dec 7, 2024 β’ 7 β’ 3
openai/whisper-large-v3 Automatic Speech Recognition β’ Updated Aug 12, 2024 β’ 5.84M β’ β’ 5.46k
Runtime error 1 PORTULAN Albertina 1b5 Portuguese Ptbr Encoder π¨ 1 Translate... Portuguese text to other languages