chatterbox Reference

Functions

• chatterbox - chatterbox(device)
• compute_mel_spectrogram - compute_mel_spectrogram(y, n_fft, n_mels, sr, hop_size, win_size, fmin, fmax, center)
• compute_mel_spectrogram_ve - compute_mel_spectrogram_ve(y, sr)
• compute_speaker_embedding - compute_speaker_embedding(model, audio, sr, overlap)
• compute_xvector_embedding - compute_xvector_embedding(model, audio, sr)
• create_s3gen_vocoder - create_s3gen_vocoder(device)
• create_voice_embedding - create_voice_embedding(model, audio, sample_rate, autocast)
• decode_tokens - decode_tokens(tokenizer, ids)
• download_chatterbox_models - download_chatterbox_models(force)
• get_model_paths - get_model_paths()
• load_bpe_tokenizer - load_bpe_tokenizer(vocab_path)
• load_campplus_weights - load_campplus_weights(model, state_dict, prefix)
• load_chatterbox - load_chatterbox(model)
• load_hifigan_weights - load_hifigan_weights(model, state_dict, prefix)
• load_s3gen - load_s3gen(path, device)
• load_s3gen_weights - load_s3gen_weights(model, state_dict)
• load_s3tokenizer_weights - load_s3tokenizer_weights(model, state_dict, prefix)
• models_available - models_available()
• quick_tts - quick_tts(text, reference_audio, output_path, device, autocast)
• read_audio - read_audio(path)
• read_safetensors - read_safetensors(path, device)
• read_torch_pt - read_torch_pt(path, device)
• resample_audio - resample_audio(samples, from_sr, to_sr)
• s3_tokenizer - s3_tokenizer(config)
• t3_inference - t3_inference(model, cond, text_tokens, max_new_tokens, temperature, cfg_weight, top_p, min_p, repetition_penalty)
• text_to_tokens - text_to_tokens(tokenizer, text, normalize, device)
• generate - generate(model, text, voice, exaggeration, cfg_weight, temperature, top_p, autocast, traced)
• tts_chunked - tts_chunked(model, text, voice, chunk_size, ...)
• tts_to_file - tts_to_file(model, text, voice, output_path, ...)
• write_audio - write_audio(samples, sr, path)

Functions

• chatterbox
  chatterbox::chatterbox
• compute_mel_spectrogram
  chatterbox::compute_mel_spectrogram
• compute_mel_spectrogram_ve
  chatterbox::compute_mel_spectrogram_ve
• compute_speaker_embedding
  chatterbox::compute_speaker_embedding
• compute_xvector_embedding
  chatterbox::compute_xvector_embedding
• create_s3gen_vocoder
  chatterbox::create_s3gen_vocoder
• create_voice_embedding
  chatterbox::create_voice_embedding
• decode_tokens
  chatterbox::decode_tokens
• download_chatterbox_models
  chatterbox::download_chatterbox_models
• generate
  chatterbox::generate
• get_model_paths
  chatterbox::get_model_paths
• load_bpe_tokenizer
  chatterbox::load_bpe_tokenizer
• load_campplus_weights
  chatterbox::load_campplus_weights
• load_chatterbox
  chatterbox::load_chatterbox
• load_hifigan_weights
  chatterbox::load_hifigan_weights
• load_s3gen
  chatterbox::load_s3gen
• load_s3gen_weights
  chatterbox::load_s3gen_weights
• load_s3tokenizer_weights
  chatterbox::load_s3tokenizer_weights
• models_available
  chatterbox::models_available
• quick_tts
  chatterbox::quick_tts
• read_audio
  chatterbox::read_audio
• read_safetensors
  chatterbox::read_safetensors
• read_torch_pt
  chatterbox::read_torch_pt
• resample_audio
  chatterbox::resample_audio
• s3_tokenizer
  chatterbox::s3_tokenizer
• t3_inference
  chatterbox::t3_inference
• text_to_tokens
  chatterbox::text_to_tokens
• tts_chunked
  chatterbox::tts_chunked
• tts_to_file
  chatterbox::tts_to_file
• write_audio
  chatterbox::write_audio