MCPcopy Create free account

hub / github.com/KoljaB/RealtimeTTS / functions

Functions1,468 in github.com/KoljaB/RealtimeTTS

↓ 3 callersMethodset_voice
(self, voice: Union[str, CartesiaVoice, Dict[str, Any]])
RealtimeTTS/engines/cartesia_engine.py:257
↓ 3 callersMethodset_voice
(self, voice: Union[ChatterboxVoice, str])
RealtimeTTS/engines/chatterbox_engine.py:120
↓ 3 callersMethodshutdown
Shutdown the engine and release resources.
RealtimeTTS/engines/pocket_engine.py:670
↓ 3 callersFunctionspectrogram_to_image
(spec, mode="magnitude")
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:127
↓ 3 callersMethodstop
Stops the playback of the synthesized audio stream immediately.
RealtimeTTS/text_to_stream.py:879
↓ 3 callersMethodsynthesize
(self)
example_rvc/xtts_rvc_synthesizer.py:87
↓ 3 callersMethodsynthesize
(self, text)
tests/test_minimax_integration.py:50
↓ 3 callersMethodunload_model
Unloads the current model and clears VRAM to prevent memory leaks. Steps: 1. Move models to CPU to ensure PyTorch releas
RealtimeTTS/engines/style_engine.py:198
↓ 3 callersMethoduse_fp32_config
(self)
example_rvc/rvc/configs/config.py:138
↓ 3 callersMethodvc_single
( self, sid, input_audio_path, f0_up_key, f0_file, f0_method,
example_rvc/rvc/infer/modules/vc/modules.py:149
↓ 3 callersMethodwait_playing
(self)
example_rvc/xtts_rvc_synthesizer.py:171
↓ 3 callersFunctionwave_to_spectrogram
( wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False )
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:30
↓ 2 callersFunctionSafePipe
Returns a pair: (thread-safe parent pipe, raw child pipe).
RealtimeTTS/engines/safepipe.py:177
↓ 2 callersMethod_contains_any
(directory: Path, filenames: tuple[str, ...])
RealtimeTTS/engines/moss_tts_engine.py:323
↓ 2 callersMethod_encode_prompt
(self, voice: LuxTTSVoice)
RealtimeTTS/engines/luxtts_engine.py:147
↓ 2 callersMethod_enqueue_silence
Adds silence of the requested duration to the engine queue.
RealtimeTTS/text_to_stream.py:1151
↓ 2 callersFunction_execute
( X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True )
example_rvc/rvc/infer/lib/uvr5_pack/utils.py:30
↓ 2 callersMethod_extract_inline_actions
Splits text into synthesis chunks and inline control actions. Registered tags are removed from the synthesized text and replaced by
RealtimeTTS/text_to_stream.py:1021
↓ 2 callersMethod_generate_tokens
Generate a token stream using the LM Studio API. Args: prompt (str): The input text prompt. Yields:
RealtimeTTS/engines/orpheus_engine.py:157
↓ 2 callersMethod_get_client
(self)
RealtimeTTS/engines/typecast_engine.py:89
↓ 2 callersMethod_get_relative_embeddings
(self, relative_embeddings, length: int)
example_rvc/rvc/infer/lib/infer_pack/attentions.py:306
↓ 2 callersMethod_install_hint
(self)
RealtimeTTS/engines/moss_tts_engine.py:170
↓ 2 callersMethod_is_engine_mpeg
Checks if the engine is an MPEG engine. Returns: Boolean indicating if the engine is an MPEG engine.
RealtimeTTS/text_to_stream.py:1175
↓ 2 callersMethod_load_voice_state
(self, state_path: Path)
RealtimeTTS/engines/pocket_gpu_engine.py:289
↓ 2 callersMethod_log_and_trigger
Log character and trigger associated callbacks.
RealtimeTTS/threadsafe_generators.py:69
↓ 2 callersMethod_normalize_num_steps_schedule
Validates and normalizes the step schedule.
RealtimeTTS/engines/omnivoice_engine.py:145
↓ 2 callersMethod_normalize_output_format
( self, output_format: Optional[Mapping[str, Any]], )
RealtimeTTS/engines/cartesia_engine.py:88
↓ 2 callersMethod_normalize_ref_codes
(ref_codes)
RealtimeTTS/engines/neutts_engine.py:263
↓ 2 callersMethod_prepare_reference
(self, voice: SoproTTSVoice)
RealtimeTTS/engines/sopro_engine.py:150
↓ 2 callersMethod_prepare_voice_prompt
Extracts features from a voice prompt, using a cache if available. The extracted features are stored in the engine's state.
RealtimeTTS/engines/zipvoice_engine.py:265
↓ 2 callersMethod_prime_cache
Insert the speaker embedding into the model's internal cache under the sentinel key. If a speaker_pt file exists, load it; otherwise
RealtimeTTS/engines/faster_qwen_engine.py:186
↓ 2 callersMethod_queue_audio
(self, wav)
RealtimeTTS/engines/soprano_engine.py:135
↓ 2 callersMethod_queue_audio
(self, audio_float32: np.ndarray)
RealtimeTTS/engines/pocket_engine.py:487
↓ 2 callersMethod_queue_audio
(self, wav)
RealtimeTTS/engines/sopro_engine.py:238
↓ 2 callersMethod_resolved_language
(self)
RealtimeTTS/engines/neutts_engine.py:143
↓ 2 callersFunction_set_engine
(engine_name)
example_fast_api/server.py:245
↓ 2 callersFunction_set_engine
(engine_name)
example_fast_api/async_server.py:328
↓ 2 callersMethod_synthesize_impl
Synthesizes text to audio stream. Args: text (str): Text to synthesize. sentence_count (int): The count of s
RealtimeTTS/engines/pocket_engine.py:527
↓ 2 callersMethod_to_numpy_audio
Convert a Pocket TTS tensor or array to flat float32 numpy audio.
RealtimeTTS/engines/pocket_engine.py:476
↓ 2 callersMethod_to_pcm16
(self, wav)
RealtimeTTS/engines/neutts_engine.py:296
↓ 2 callersMethod_token_decoder
Decode tokens from the generator and convert them into audio samples. This method aggregates tokens in a buffer and converts them in
RealtimeTTS/engines/orpheus_engine.py:234
↓ 2 callersMethod_validate_output_format
(self, output_format: Mapping[str, Any])
RealtimeTTS/engines/cartesia_engine.py:106
↓ 2 callersMethod_voice
(self)
RealtimeTTS/engines/moss_tts_engine.py:395
↓ 2 callersMethod_voice_cache_key
(self, voice: SoproTTSVoice)
RealtimeTTS/engines/sopro_engine.py:139
↓ 2 callersMethod_warmup
Performs a warm-up generation run to initialize GPU caches.
RealtimeTTS/engines/omnivoice_engine.py:180
↓ 2 callersMethodadd
Add a string or a string iterator to the list of items.
RealtimeTTS/threadsafe_generators.py:57
↓ 2 callersMethodadd_voice
Registers a voice switch tag. Args: tag (str): Tag content without delimiters, for example "angry". voice: V
RealtimeTTS/text_to_stream.py:293
↓ 2 callersFunctionamp_to_db
Convert the input tensor from amplitude to decibel scale. Arguments: x {[torch.Tensor]} -- [Input tensor.] Keyword Arguments:
example_rvc/rvc/tools/torchgate/utils.py:6
↓ 2 callersFunctionaudio_chunk_generator
Generate audio chunks, converting format if necessary. Collects all audio, detects format, converts if needed, then creates a complete WAV fi
example_fast_api/server.py:319
↓ 2 callersMethodclear_queue
(self)
example_rvc/rvc/realtimervc.py:566
↓ 2 callersFunctioncompute_mask_indices
Computes random mask spans for a given shape Args: shape: the the shape for which to compute masks. should be of size 2
example_rvc/rvc/infer/lib/jit/get_hubert.py:95
↓ 2 callersFunctionconvert_audio_to_pcm
Convert audio data from various formats to raw PCM. Returns: (pcm_data, sample_rate, channels, sample_width)
example_fast_api/async_server.py:83
↓ 2 callersFunctionconvert_pad_shape
(pad_shape: List[List[int]])
example_rvc/rvc/infer/lib/infer_pack/commons.py:121
↓ 2 callersFunctioncreate_complete_wav_file
Create a complete WAV file with proper headers and data.
example_fast_api/async_server.py:132
↓ 2 callersFunctioncreate_generator
Create a text generator for a single text string
tests/orpheus_test.py:51
↓ 2 callersMethodcreate_worker_process
(self)
RealtimeTTS/engines/coqui_engine.py:217
↓ 2 callersFunctiondetect_audio_format
Detect audio format from the first few bytes of a chunk. Returns: 'mp3', 'wav', 'ogg', or 'pcm'
example_fast_api/async_server.py:58
↓ 2 callersMethodensure_playing
(self)
example_rvc/xtts_rvc_synthesizer.py:64
↓ 2 callersFunctioneval
(model, n, input)
example_rvc/rvc/tools/calc_rvc_model_similarity.py:46
↓ 2 callersFunctionexport
( model: torch.nn.Module, mode: str = "trace", inputs: dict = None, device=torch.device("cpu")
example_rvc/rvc/infer/lib/jit/__init__.py:76
↓ 2 callersFunctionextract
(ckpt)
example_rvc/rvc/infer/lib/train/process_ckpt.py:208
↓ 2 callersFunctionfetchVoices
()
example_fast_api/static/tts.js:187
↓ 2 callersFunctionfft_hp_filter
(spec, bin_start, bin_stop)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:437
↓ 2 callersMethodforward
(self, x)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_new.py:78
↓ 2 callersMethodgenerate_audio_stream
(self, voice_state, text, **kwargs)
tests/test_pocket_engine.py:12
↓ 2 callersFunctiongenerator
()
tests/orpheus_test.py:53
↓ 2 callersMethodget_f0
(self, x, f0_up_key, n_cpu, method="harvest")
example_rvc/rvc/tools/rvc_for_realtime.py:222
↓ 2 callersFunctionget_rmvpe
(model_path="rvc/assets/rmvpe/rmvpe.pt", device=torch.device("cpu"))
example_rvc/rvc/infer/lib/jit/get_rmvpe.py:4
↓ 2 callersFunctionget_timing_signal_1d
(length, channels, min_timescale=1.0, max_timescale=1.0e4)
example_rvc/rvc/infer/lib/infer_pack/commons.py:72
↓ 2 callersMethodget_vc
(self, sid, *to_return_protect)
example_rvc/rvc/infer/modules/vc/modules.py:39
↓ 2 callersFunctiongo
(model, bkey)
example_rvc/rvc/infer/lib/train/utils.py:24
↓ 2 callersFunctiongradscaler_init
()
example_rvc/rvc/infer/modules/ipex/gradscaler.py:180
↓ 2 callersFunctioninference
data : dic configs
example_rvc/rvc/infer/lib/uvr5_pack/utils.py:25
↓ 2 callersMethodinit
(self)
example_rvc/rvc/realtimervc.py:509
↓ 2 callersMethodinterpolate_f0
对F0进行插值处理
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py:14
↓ 2 callersMethodinterpolate_f0
对F0进行插值处理
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py:14
↓ 2 callersMethodinterpolate_f0
对F0进行插值处理
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py:14
↓ 2 callersMethodinverse
Call the inverse STFT (iSTFT), given magnitude and phase tensors produced by the ```transform``` function. Arguments: mag
example_rvc/rvc/infer/lib/rmvpe.py:115
↓ 2 callersFunctionis_browser_request
(request)
example_fast_api/server.py:289
↓ 2 callersFunctionload_filepaths_and_text
(filename, split="|")
example_rvc/rvc/infer/lib/train/utils.py:279
↓ 2 callersFunctionload_wav_to_torch
(full_path)
example_rvc/rvc/infer/lib/train/utils.py:274
↓ 2 callersMethodload_xtts_model
(self, local_path: str = None)
example_rvc/xtts_rvc_synthesizer.py:96
↓ 2 callersFunctionmake_padding
(width, cropsize, offset)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/dataset.py:118
↓ 2 callersFunctionmake_voice
(name: str)
tests/omnivoice_emotions.py:54
↓ 2 callersFunctionmodel_hash
(filename)
example_rvc/rvc/tools/calc_rvc_model_similarity.py:32
↓ 2 callersMethodnorm_write
(self, tmp_audio, idx0, idx1)
example_rvc/rvc/infer/modules/train/preprocess.py:61
↓ 2 callersMethodon_audio_chunk
(self, chunk)
example_fast_api/async_server.py:215
↓ 2 callersMethodon_audio_stream_stop
(self)
example_fast_api/async_server.py:218
↓ 2 callersFunctionpad_to_multiple
(x, multiple, dim=-1, value=0)
example_rvc/rvc/infer/lib/jit/get_hubert.py:14
↓ 2 callersMethodpadding
(self, x: torch.Tensor, x_mask: torch.Tensor)
example_rvc/rvc/infer/lib/infer_pack/attentions.py:415
↓ 2 callersMethodpost_init
(self)
RealtimeTTS/engines/camb_engine.py:59
↓ 2 callersMethodreset_audio_duration
Resets the audio duration to 0.
RealtimeTTS/engines/base_engine.py:65
↓ 2 callersMethodresize_f0
(self, x, target_len)
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py:52
↓ 2 callersMethodresize_f0
(self, x, target_len)
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py:52
↓ 2 callersMethodresume
Resumes paused audio playback.
RealtimeTTS/stream_player.py:729
↓ 2 callersFunctionsave
(ckpt: dict, save_path: str)
example_rvc/rvc/infer/lib/jit/__init__.py:107
↓ 2 callersFunctionsavee
(ckpt, sr, if_f0, name, epoch, version, hps)
example_rvc/rvc/infer/lib/train/process_ckpt.py:12
↓ 2 callersFunctionsearchsorted
(bin_locations, inputs, eps=1e-6)
example_rvc/rvc/infer/lib/infer_pack/transforms.py:43
↓ 2 callersFunctionsetMode
(mode)
example_fast_api/static/tts.js:146
↓ 2 callersMethodset_model
(self, model_name)
example_rvc/rvc/realtimervc.py:623
← previousnext →101–200 of 1,468, ranked by callers