MCPcopy Create free account

hub / github.com/KoljaB/RealtimeTTS / functions

Functions1,468 in github.com/KoljaB/RealtimeTTS

↓ 2 callersFunctionset_speaking
(text, status)
example_fast_api/server.py:389
↓ 2 callersMethodset_speed
Sets the speed of the speech synthesis.
RealtimeTTS/engines/coqui_engine.py:826
↓ 2 callersMethodset_volume
Set the playback volume. Args: volume (float): Volume level from 0.0 (muted) to 1.0 (full volume)
RealtimeTTS/text_to_stream.py:269
↓ 2 callersMethodshutdown
(self)
example_rvc/rvc/realtimervc.py:579
↓ 2 callersMethodslice
(self, waveform)
example_rvc/rvc/infer/lib/slicer2.py:75
↓ 2 callersFunctionspeakWebSocket
()
example_fast_api/static/tts.js:25
↓ 2 callersFunctionspeak_and_wait
Feed text/generator to the TTS stream and block until playback ends.
tests/camb_test.py:81
↓ 2 callersFunctionspec_to_mel_torch
(spec, n_fft, num_mels, sampling_rate, fmin, fmax)
example_rvc/rvc/infer/lib/train/mel_processing.py:92
↓ 2 callersMethodstart_stream
Starts the audio stream.
RealtimeTTS/stream_player.py:311
↓ 2 callersMethodstart_vc
(self)
example_rvc/rvc/realtimervc.py:89
↓ 2 callersMethodstop
(self)
example_rvc/xtts_rvc_synthesizer.py:179
↓ 2 callersMethodsynthesize
Synthesizes text to audio stream. Args: text (str): Text to synthesize. sentence_count (int): The count of s
RealtimeTTS/engines/base_engine.py:223
↓ 2 callersMethodsynthesize
(self, text: str, sentence_count: int = 0)
RealtimeTTS/engines/pocket_engine.py:524
↓ 2 callersFunctiontrain_and_evaluate
( rank, epoch, hps, nets, optims, schedulers, scaler, loaders, logger, writers, cache )
example_rvc/rvc/infer/modules/train/train.py:300
↓ 2 callersMethodunload_model
(self)
example_rvc/rvc/realtimervc.py:616
↓ 1 callersMethod__init__
(self, args)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:91
↓ 1 callersMethod__init__
(self, orig_func, sub_func, cond_func)
example_rvc/rvc/infer/modules/ipex/hijacks.py:30
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16, 32))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_33966KB.py:9
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_537227KB.py:9
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_537238KB.py:9
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_123812KB.py:9
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_61968KB.py:9
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets.py:8
↓ 1 callersMethod__init__
(self, nin, ch, dilations=(4, 8, 16))
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_123821KB.py:9
↓ 1 callersMethod__init__
( self, nin, nout, nin_lstm, nout_lstm, dilations=((4, 2), (8, 4), (12, 6)) )
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/nets_new.py:9
↓ 1 callersMethod__init__
(self, audiopaths_and_text, hparams)
example_rvc/rvc/infer/lib/train/data_utils.py:230
↓ 1 callersMethod__init__
(self, name)
RealtimeTTS/engines/coqui_engine.py:46
↓ 1 callersMethod__init__
( self, name: str, ref_audio: Optional[str] = None, ref_text:
RealtimeTTS/engines/faster_qwen_engine.py:55
↓ 1 callersMethod__init__
(self, name: str)
RealtimeTTS/engines/orpheus_engine.py:36
↓ 1 callersMethod__init__
( self, name: str, language_code: str = None )
RealtimeTTS/engines/kokoro_engine.py:65
↓ 1 callersMethod__init__
(self, name: str, ref_audio_path: str, ref_text: str, ref_codes=None)
RealtimeTTS/engines/neutts_engine.py:29
↓ 1 callersMethod__init__
(self, start_time, end_time, word)
RealtimeTTS/engines/base_engine.py:15
↓ 1 callersMethod__init__
(self, name, locale, gender)
RealtimeTTS/engines/azure_engine.py:30
↓ 1 callersMethod__init__
Initialize a PocketTTS voice. Args: name: Voice identifier (built-in name or custom name for cloned voice) a
RealtimeTTS/engines/pocket_engine.py:118
↓ 1 callersMethod__init__
( self, name: str, audio_prompt_path: Optional[str] = None, state_path: Option
RealtimeTTS/engines/pocket_gpu_engine.py:39
↓ 1 callersMethod__init__
(self, name, description)
RealtimeTTS/engines/parler_engine.py:12
↓ 1 callersMethod__init__
( self, name: str, ref_audio: str, ref_text: str,
RealtimeTTS/engines/omnivoice_engine.py:34
↓ 1 callersMethod_absolute_position_to_relative_position
x: [b, h, l, l] ret: [b, h, l, 2*l-1]
example_rvc/rvc/infer/lib/infer_pack/attentions.py:352
↓ 1 callersMethod_attention_bias_proximal
Bias for self-attention to encourage attention to close positions. Args: length: an integer scalar. Returns: a Ten
example_rvc/rvc/infer/lib/infer_pack/attentions.py:374
↓ 1 callersMethod_audio_array_to_pcm16
(self, waveform)
RealtimeTTS/engines/moss_tts_engine.py:404
↓ 1 callersMethod_auto_local_config
(self)
RealtimeTTS/engines/pocket_gpu_engine.py:162
↓ 1 callersMethod_auto_voice_cloning_config
(self)
RealtimeTTS/engines/pocket_engine.py:299
↓ 1 callersMethod_bisect
(self, x, lo=0, hi=None)
example_rvc/rvc/infer/lib/train/data_utils.py:501
↓ 1 callersMethod_build_prompt
Builds the appropriate prompt object based on emotion_type and model.
RealtimeTTS/engines/typecast_engine.py:104
↓ 1 callersMethod_cache_metadata_matches
(cached_data, expected_metadata)
RealtimeTTS/engines/zipvoice_engine.py:258
↓ 1 callersMethod_cached_state_path
(self, voice_name: str, audio_path: str)
RealtimeTTS/engines/pocket_engine.py:404
↓ 1 callersMethod_cached_state_path
(self, voice_name: str, audio_path: str)
RealtimeTTS/engines/pocket_gpu_engine.py:218
↓ 1 callersMethod_causal_padding
(self, x)
example_rvc/rvc/infer/lib/infer_pack/attentions.py:433
↓ 1 callersMethod_configure_streaming
(self)
RealtimeTTS/engines/neutts_engine.py:148
↓ 1 callersMethod_convert_buffer
Convert a buffer of token frames into audio samples. This method uses an external decoder to convert the collected token frames.
RealtimeTTS/engines/orpheus_engine.py:299
↓ 1 callersMethod_create_buckets
(self)
example_rvc/rvc/infer/lib/train/data_utils.py:429
↓ 1 callersMethod_cuda_dll_candidate_dirs
(self)
RealtimeTTS/engines/moss_tts_engine.py:269
↓ 1 callersMethod_decode_onnx_audio
(self, audio, audio_length: int)
RealtimeTTS/engines/moss_tts_engine.py:443
↓ 1 callersFunction_disable_torchcodec_for_windows
Avoid Transformers selecting torchcodec on Windows. The LuxTTS Gradio Windows setup disables this to avoid DLL/ffmpeg mismatch crashes d
RealtimeTTS/engines/luxtts_engine.py:13
↓ 1 callersMethod_encoding_to_pyaudio_format
(self)
RealtimeTTS/engines/cartesia_engine.py:120
↓ 1 callersMethod_execution_provider_is_cuda
(self)
RealtimeTTS/engines/moss_tts_engine.py:225
↓ 1 callersMethod_export_voice_state
(self, voice_state, state_path: Path)
RealtimeTTS/engines/pocket_engine.py:453
↓ 1 callersMethod_extract_audio_bytes
(self, response: Any)
RealtimeTTS/engines/cartesia_engine.py:146
↓ 1 callersMethod_extract_speaker_embedding
Extract the speaker embedding from reference audio/text using the loaded model. This is a one‑time operation per voice; the result is
RealtimeTTS/engines/faster_qwen_engine.py:158
↓ 1 callersMethod_extract_voice_language
(locale)
RealtimeTTS/engines/azure_engine.py:48
↓ 1 callersMethod_extract_voice_name
(full_name)
RealtimeTTS/engines/azure_engine.py:41
↓ 1 callersMethod_f02uv
(self, f0)
example_rvc/rvc/infer/lib/infer_pack/models.py:378
↓ 1 callersMethod_f02uv
(self, f0)
example_rvc/rvc/infer/lib/infer_pack/models_onnx.py:314
↓ 1 callersMethod_file_sha256
(path: str)
RealtimeTTS/engines/zipvoice_engine.py:212
↓ 1 callersMethod_filter
Filter text & store spec lengths
example_rvc/rvc/infer/lib/train/data_utils.py:34
↓ 1 callersMethod_filter
Filter text & store spec lengths
example_rvc/rvc/infer/lib/train/data_utils.py:242
↓ 1 callersMethod_find_kyutai_snapshot
(self)
RealtimeTTS/engines/pocket_gpu_engine.py:198
↓ 1 callersMethod_format_prompt
Format the text prompt with special tokens required by Orpheus. Args: prompt (str): The raw text prompt. Return
RealtimeTTS/engines/orpheus_engine.py:222
↓ 1 callersMethod_generate_and_queue_audio
Generates audio from text, buffers audio for a set duration, and then streams it into the audio queue. Args: text (str):
RealtimeTTS/engines/parler_engine.py:93
↓ 1 callersMethod_generate_mask_smoothing_filter
A PyTorch module that applies a spectral gate to an input signal using the STFT. Returns: smoothing_filter (torch.Tensor
example_rvc/rvc/tools/torchgate/torchgate.py:75
↓ 1 callersMethod_get_best_sample_rate
Determines the best available sample rate for the device. Args: device_index: Index of the audio device desi
RealtimeTTS/stream_player.py:136
↓ 1 callersMethod_get_num_steps_for_sentence
Returns the configured number of steps for the given sentence index. Behavior: - first sentence -> first entry - sec
RealtimeTTS/engines/omnivoice_engine.py:162
↓ 1 callersMethod_get_pipeline
Retrieves the KPipeline for the specified language code. Args: lang_code (str): The language code for which to get the p
RealtimeTTS/engines/kokoro_engine.py:188
↓ 1 callersMethod_get_sample_rate_from_config
Reads the sample rate from the Piper voice configuration file. Returns: int: Sample rate from config, or 16000 a
RealtimeTTS/engines/piper_engine.py:71
↓ 1 callersFunction_get_stream2sentence
Import stream2sentence only when sentence splitting is actually used.
RealtimeTTS/text_to_stream.py:37
↓ 1 callersMethod_get_voice_state
Get or create a voice state for the given voice. Args: voice: Voice identifier or PocketTTSVoice object Returns
RealtimeTTS/engines/pocket_engine.py:336
↓ 1 callersMethod_get_voice_state
(self, voice: Union[str, PocketTTSGpuVoice])
RealtimeTTS/engines/pocket_gpu_engine.py:308
↓ 1 callersMethod_handle_timestamps
(self, response: Any)
RealtimeTTS/engines/cartesia_engine.py:169
↓ 1 callersFunction_import_minimax_engine
Import minimax_engine in isolation without triggering full RealtimeTTS init.
tests/test_minimax_integration.py:25
↓ 1 callersFunction_import_minimax_engine
Import minimax_engine in isolation without triggering full RealtimeTTS init.
tests/test_minimax_engine.py:20
↓ 1 callersMethod_init_model
Initialize the NeuTTS model.
RealtimeTTS/engines/neutts_engine.py:164
↓ 1 callersMethod_init_onnx_runtime
(self)
RealtimeTTS/engines/moss_tts_engine.py:188
↓ 1 callersMethod_init_runtime
(self)
RealtimeTTS/engines/moss_tts_engine.py:177
↓ 1 callersMethod_init_torch_runtime
(self)
RealtimeTTS/engines/moss_tts_engine.py:330
↓ 1 callersMethod_is_gguf_backbone
(self)
RealtimeTTS/engines/neutts_engine.py:117
↓ 1 callersMethod_load_model
Load the Pocket TTS model.
RealtimeTTS/engines/pocket_engine.py:267
↓ 1 callersMethod_load_model
(self)
RealtimeTTS/engines/pocket_gpu_engine.py:116
↓ 1 callersMethod_load_voices
Load voice references from an optional voices directory.
RealtimeTTS/engines/neutts_engine.py:196
↓ 1 callersMethod_lowpass
(self, audio)
RealtimeTTS/engines/sopro_engine.py:222
↓ 1 callersMethod_make_error_response
Create a mock error API response.
tests/test_minimax_engine.py:321
↓ 1 callersMethod_matmul_with_relative_keys
x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]
example_rvc/rvc/infer/lib/infer_pack/attentions.py:297
↓ 1 callersMethod_matmul_with_relative_values
x: [b, h, l, m] y: [h or 1, m, d] ret: [b, h, l, d]
example_rvc/rvc/infer/lib/infer_pack/attentions.py:288
↓ 1 callersMethod_nonstationary_mask
Computes a non-stationary binary mask to filter out noise in a log-magnitude spectrogram. Arguments: X_abs (torch.Tensor
example_rvc/rvc/tools/torchgate/torchgate.py:178
↓ 1 callersMethod_normalize_backend
(backend: str)
RealtimeTTS/engines/moss_tts_engine.py:162
↓ 1 callersMethod_normalize_variant
(variant: str)
RealtimeTTS/engines/moss_tts_engine.py:153
↓ 1 callersMethod_onnx_prompt_audio_codes
(self, voice: MossTTSVoice)
RealtimeTTS/engines/moss_tts_engine.py:437
↓ 1 callersMethod_output_path
(self)
RealtimeTTS/engines/moss_tts_engine.py:400
↓ 1 callersMethod_package_config_path
(self)
RealtimeTTS/engines/pocket_gpu_engine.py:193
↓ 1 callersMethod_parse_mixed_voice_formula
Parse a formula like "0.3*af_sarah + 0.7*am_adam" to create a weighted blend of voice Tensors. Args: formula (str): Weig
RealtimeTTS/engines/kokoro_engine.py:207
↓ 1 callersMethod_parse_pause_override
Parses inline pause overrides like 'pause=0.5', 'pause: 0.5' or 'pause 0.5'.
RealtimeTTS/text_to_stream.py:1106
← previousnext →201–300 of 1,468, ranked by callers