How to use mkieffer/funny with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("mkieffer/funny") voice_state = tts_model.get_state_for_audio_prompt( "hf://kyutai/tts-voices/alba-mackenna/casual.wav" ) audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.") # Audio is a 1D torch tensor containing PCM data. scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy())
just a funny guy
uvx --from "pocket-tts @ git+https://github.com/kyutai-labs/pocket-tts.git" pocket-tts generate \ --voice hf://mkieffer/funny/embeddings/funny-1.safetensors \ --text "Hello there! I'm just a funny guy" \ --output-path output.wav