Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/KoljaB/RealtimeTTS
/ functions
Functions
1,468 in github.com/KoljaB/RealtimeTTS
⨍
Functions
1,468
◇
Types & classes
238
↳
Endpoints
29
↓ 1 callers
Function
main
()
main.py:1
↓ 1 callers
Function
main
(path, root)
example_rvc/rvc/tools/calc_rvc_model_similarity.py:56
↓ 1 callers
Function
main
()
example_rvc/rvc/tools/infer_cli.py:41
↓ 1 callers
Function
main
()
example_rvc/rvc/tools/infer_batch_rvc.py:40
↓ 1 callers
Function
main
()
example_rvc/rvc/infer/modules/train/train.py:93
↓ 1 callers
Function
main
()
example_rvc/rvc/infer/lib/slicer2.py:182
↓ 1 callers
Function
main
Main translation loop.
tests/translator.py:50
↓ 1 callers
Function
main
Main loop for interaction.
tests/openai_voice_interface.py:46
↓ 1 callers
Function
main
()
tests/orpheus_test.py:57
↓ 1 callers
Function
main
()
example_fast_api/websocket_client.py:175
↓ 1 callers
Function
make_padding
(width, cropsize, offset)
example_rvc/rvc/infer/lib/uvr5_pack/utils.py:15
↓ 1 callers
Method
mel2hidden
(self, mel)
example_rvc/rvc/infer/lib/rmvpe.py:569
↓ 1 callers
Function
mel_spectrogram_torch
Convert waveform into Mel-frequency Log-amplitude spectrogram. Args: y :: (B, T) - Waveforms Returns: melspec
example_rvc/rvc/infer/lib/train/mel_processing.py:111
↓ 1 callers
Method
mute
Mutes audio playback.
RealtimeTTS/stream_player.py:733
↓ 1 callers
Method
on_audio_stream_start
(self)
tests/pyqt6_speed_test.py:92
↓ 1 callers
Method
open_stream
Opens an audio stream.
RealtimeTTS/stream_player.py:201
↓ 1 callers
Function
parse_requirements
(filename)
setup.py:59
↓ 1 callers
Function
piecewise_rational_quadratic_transform
( inputs, unnormalized_widths, unnormalized_heights, unnormalized_derivatives, inverse=Fal
example_rvc/rvc/infer/lib/infer_pack/transforms.py:10
↓ 1 callers
Method
pipeline
( self, model, net_g, sid, audio, input_audio_path, ti
example_rvc/rvc/infer/modules/vc/pipeline.py:281
↓ 1 callers
Method
pipeline
(self, path, idx0)
example_rvc/rvc/infer/modules/train/preprocess.py:83
↓ 1 callers
Method
pipeline_mp
(self, infos)
example_rvc/rvc/infer/modules/train/preprocess.py:109
↓ 1 callers
Method
pipeline_mp_inp_dir
(self, inp_root, n_p)
example_rvc/rvc/infer/modules/train/preprocess.py:113
↓ 1 callers
Function
playAudio
()
example_fast_api/static/tts.js:112
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/faster_qwen_engine.py:155
↓ 1 callers
Method
post_init
Set up additional engine attributes.
RealtimeTTS/engines/orpheus_engine.py:91
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/style_engine.py:195
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/soprano_engine.py:85
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/piper_engine.py:68
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/cartesia_engine.py:85
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/zipvoice_engine.py:324
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/chatterbox_engine.py:109
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/sopro_engine.py:128
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/luxtts_engine.py:127
↓ 1 callers
Method
post_init
(self)
RealtimeTTS/engines/omnivoice_engine.py:142
↓ 1 callers
Method
prediction
(self, m, vocal_root, others_root, format)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:199
↓ 1 callers
Function
prepare_voices
(engine: FasterQwenEngine, entries: List[EmotionEntry])
tests/faster_qwen_emotions.py:208
↓ 1 callers
Function
preprocess
(X_spec)
example_rvc/rvc/infer/lib/uvr5_pack/utils.py:55
↓ 1 callers
Function
preprocess_trainset
(inp_root, sr, n_p, exp_dir, per)
example_rvc/rvc/infer/modules/train/preprocess.py:136
↓ 1 callers
Function
process_requests
Process queued requests one by one
example_fast_api/async_server.py:489
↓ 1 callers
Function
rand_gumbel
Sample from the Gumbel distribution, protect from overflows.
example_rvc/rvc/infer/lib/infer_pack/commons.py:33
↓ 1 callers
Function
rational_quadratic_spline
( inputs, unnormalized_widths, unnormalized_heights, unnormalized_derivatives, inverse=Fal
example_rvc/rvc/infer/lib/infer_pack/transforms.py:98
↓ 1 callers
Function
readwave
(wav_path, normalize=False)
example_rvc/rvc/infer/modules/train/extract_feature_print.py:64
↓ 1 callers
Method
receive_audio
Receive and play audio from the server
example_fast_api/websocket_client.py:62
↓ 1 callers
Function
receive_messages
Receive and queue text messages
example_fast_api/async_server.py:557
↓ 1 callers
Method
record
(self)
example_rvc/rvc/infer/modules/train/train.py:84
↓ 1 callers
Function
reduce_vocal_aggressively
(X, y, softmask)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:151
↓ 1 callers
Method
remove_voice
Removes a registered voice switch tag. Args: tag (str): Tag content without delimiters. Returns: Se
RealtimeTTS/text_to_stream.py:317
↓ 1 callers
Method
remove_weight_norm
(self)
example_rvc/rvc/infer/lib/infer_pack/models.py:1201
↓ 1 callers
Function
request_tts
(text)
example_fast_api/client.py:109
↓ 1 callers
Method
resume
Resumes a previously paused playback of the synthesized audio stream - won't work properly with elevenlabs
RealtimeTTS/text_to_stream.py:870
↓ 1 callers
Method
retrieve_coqui_voices
Retrieves the installed voices available for the Coqui TTS engine.
RealtimeTTS/engines/coqui_engine.py:1152
↓ 1 callers
Method
save_audio_to_file
Save received audio to a WAV file
example_fast_api/websocket_client.py:144
↓ 1 callers
Function
select_language
Display language options and get user's choice.
tests/translator.py:43
↓ 1 callers
Method
send_messages
Send text messages to the server
example_fast_api/websocket_client.py:46
↓ 1 callers
Function
sequence_mask
(length: torch.Tensor, max_length: Optional[int] = None)
example_rvc/rvc/infer/lib/infer_pack/commons.py:130
↓ 1 callers
Function
setEngine
()
example_fast_api/static/tts.js:182
↓ 1 callers
Method
set_all_parameters
Updates model config, checkpoint, and reference audio simultaneously, reloading the model only once.
RealtimeTTS/engines/style_engine.py:254
↓ 1 callers
Method
set_api_key
Sets the elevenlabs api key. Args: api_key (str): Elevenlabs API key. (TTS API key)
RealtimeTTS/engines/elevenlabs_engine.py:120
↓ 1 callers
Method
set_seeds
(self, seed = 0)
RealtimeTTS/engines/style_engine.py:183
↓ 1 callers
Method
set_service_region
Sets the azure service region. Args: service_region (str): Azure service region. (Cloud Region ID)
RealtimeTTS/engines/azure_engine.py:309
↓ 1 callers
Method
set_speech_key
Sets the Azure subscription key. Args: speech_key (str): Azure subscription key (TTS API key).
RealtimeTTS/engines/azure_engine.py:300
↓ 1 callers
Method
set_speed
Sets the speed for speech synthesis. Args: speed (float): The speed factor (e.g., 1.0 for normal speed).
RealtimeTTS/engines/kokoro_engine.py:425
↓ 1 callers
Method
set_voice
Sets the voice configuration. If a speaker embedding file is provided, it is loaded once and cached. Otherwise, the reference audio/t
RealtimeTTS/engines/faster_qwen_engine.py:374
↓ 1 callers
Method
set_voice
Set the current voice for synthesis. Args: voice (Union[str, OrpheusVoice]): The voice name or an OrpheusVoice instance.
RealtimeTTS/engines/orpheus_engine.py:332
↓ 1 callers
Method
set_voice
Updates the current voice or voice formula. If it's a single voice (e.g. "af_heart"), we detect language as usual. If it contains '*'
RealtimeTTS/engines/kokoro_engine.py:396
↓ 1 callers
Method
set_voice
Set the active reference voice.
RealtimeTTS/engines/neutts_engine.py:360
↓ 1 callers
Method
set_voice
Sets the voice to be used for speech synthesis. Args: voice (Union[str, GTTSVoice]): The voice to be used for speech syn
RealtimeTTS/engines/gtts_engine.py:127
↓ 1 callers
Method
set_voice
Sets the voice to be used for speech synthesis. Args: voice (Union[str, SystemVoice]): The voice to be used for speech s
RealtimeTTS/engines/system_engine.py:112
↓ 1 callers
Method
set_voice
Set the current voice for synthesis. Args: voice: Voice identifier (string) or PocketTTSVoice object
RealtimeTTS/engines/pocket_engine.py:610
↓ 1 callers
Method
set_voice
(self, voice: Union[str, PocketTTSGpuVoice])
RealtimeTTS/engines/pocket_gpu_engine.py:407
↓ 1 callers
Method
set_voice
(self, voice: Union[SoproTTSVoice, str])
RealtimeTTS/engines/sopro_engine.py:166
↓ 1 callers
Method
set_voice
(self, voice: Union[str, MossTTSVoice])
RealtimeTTS/engines/moss_tts_engine.py:363
↓ 1 callers
Method
set_voice
(self, voice: Union[LuxTTSVoice, str])
RealtimeTTS/engines/luxtts_engine.py:162
↓ 1 callers
Method
set_voice
Sets the voice to be used for speech synthesis.
RealtimeTTS/engines/edge_engine.py:170
↓ 1 callers
Method
set_voice
Sets the voice configuration.
RealtimeTTS/engines/omnivoice_engine.py:315
↓ 1 callers
Method
setup_audio_stream
Setup PyAudio stream for playback
example_fast_api/websocket_client.py:127
↓ 1 callers
Method
shutdown
Shuts down the engine by terminating the process and closing the pipes.
RealtimeTTS/engines/coqui_engine.py:1087
↓ 1 callers
Method
shutdown
(self)
RealtimeTTS/engines/zipvoice_engine.py:398
↓ 1 callers
Method
shutdown
(self)
RealtimeTTS/engines/pocket_gpu_engine.py:429
↓ 1 callers
Function
shutdown_all_engines
(app)
tests/multilang_test_textual.py:681
↓ 1 callers
Function
shutdown_engine
(engine_name, engine)
tests/multilang_test_textual.py:672
↓ 1 callers
Function
slice_segments
(x, ids_str, segment_size=4)
example_rvc/rvc/infer/lib/infer_pack/commons.py:44
↓ 1 callers
Method
speak
(self)
tests/multilang_test_textual.py:598
↓ 1 callers
Function
speakHTTP
()
example_fast_api/static/tts.js:10
↓ 1 callers
Function
spectral_normalize_torch
(magnitudes)
example_rvc/rvc/infer/lib/train/mel_processing.py:29
↓ 1 callers
Function
synthesize
(engine, generator)
tests/chinese_test.py:8
↓ 1 callers
Function
synthesize
(engine, language, generator)
tests/multilang_tts_test.py:69
↓ 1 callers
Method
synthesize
(self, text: str, sentence_count: int = 0)
RealtimeTTS/engines/pocket_gpu_engine.py:367
↓ 1 callers
Method
synthesize
(self, text: str, sentence_count: int = 0)
RealtimeTTS/engines/moss_tts_engine.py:597
↓ 1 callers
Function
temperature_sigmoid
Apply a sigmoid function with temperature scaling. Arguments: x {[torch.Tensor]} -- [Input tensor.] x0 {[float]} -- [Paramet
example_rvc/rvc/tools/torchgate/utils.py:29
↓ 1 callers
Method
to_local_average_cents
(self, salience, thred=0.05)
example_rvc/rvc/infer/lib/rmvpe.py:622
↓ 1 callers
Function
tokens_decoder
(token_gen)
RealtimeTTS/engines/orpheus_decoder.py:94
↓ 1 callers
Method
trim_silence_end
Removes trailing silence from audio_data, applies extra trimming, and fades-out if trimming occurred. Args: audio_data (
RealtimeTTS/engines/base_engine.py:136
↓ 1 callers
Method
trim_silence_start
Removes leading silence from audio_data, applies extra trimming, and fades-in if trimming occurred. Args: audio_data (np
RealtimeTTS/engines/base_engine.py:99
↓ 1 callers
Function
turn_token_into_id
(token_string, index)
RealtimeTTS/engines/orpheus_decoder.py:69
↓ 1 callers
Method
turn_token_into_id
Convert a token string to a numeric ID for audio processing. The conversion takes into account the custom token prefix and an index-
RealtimeTTS/engines/orpheus_engine.py:268
↓ 1 callers
Function
undo_pad
(a, b, c)
example_rvc/rvc/infer/lib/jit/get_hubert.py:83
↓ 1 callers
Method
update_engines_language
(self, language)
tests/multilang_test_textual.py:580
↓ 1 callers
Function
validate_entries
(entries: List[EmotionEntry])
tests/faster_qwen_emotions.py:196
↓ 1 callers
Function
wav2
(i, o, format)
example_rvc/rvc/infer/lib/audio.py:10
← previous
next →
501–600 of 1,468, ranked by callers