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
_patch_pocket_tts_serial_streaming
Avoid PocketTTS' per-call decoder thread on Windows/Torch CPU. PocketTTS' public streaming path creates a fresh decoder worker thread for eve
RealtimeTTS/engines/pocket_engine.py:30
↓ 1 callers
Method
_pcm16_prompt_path
(self, voice_name: str, audio_path: str)
RealtimeTTS/engines/pocket_engine.py:417
↓ 1 callers
Method
_pcm16_prompt_path
(self, voice_name: str, audio_path: str)
RealtimeTTS/engines/pocket_gpu_engine.py:231
↓ 1 callers
Method
_play_chunk
Plays a chunk of audio data. Args: chunk: Chunk of audio data to be played.
RealtimeTTS/stream_player.py:630
↓ 1 callers
Method
_play_mpeg_chunk
Plays a chunk of audio data using mpv. Args: chunk: Chunk of audio data to be played.
RealtimeTTS/stream_player.py:495
↓ 1 callers
Method
_play_wav_chunk
(self, chunk)
RealtimeTTS/stream_player.py:527
↓ 1 callers
Method
_prepare_onnx_cuda_dlls
(self)
RealtimeTTS/engines/moss_tts_engine.py:229
↓ 1 callers
Method
_prepare_text_for_synthesis
Splits and cleans a text for speech synthesis. Args: text (str): Text to prepare for synthesis. Returns:
RealtimeTTS/engines/coqui_engine.py:867
↓ 1 callers
Method
_prompt_cache_key
(self, voice: LuxTTSVoice)
RealtimeTTS/engines/luxtts_engine.py:135
↓ 1 callers
Method
_prompt_cache_metadata
(self, voice: ZipVoiceVoice)
RealtimeTTS/engines/zipvoice_engine.py:228
↓ 1 callers
Method
_prompt_cache_path
(self, cache_dir: str, voice: ZipVoiceVoice)
RealtimeTTS/engines/zipvoice_engine.py:247
↓ 1 callers
Method
_queue_audio
(self, audio_float32: np.ndarray)
RealtimeTTS/engines/pocket_gpu_engine.py:358
↓ 1 callers
Method
_reapply_active_voice
Reapplies the currently active mapped voice after an engine reload.
RealtimeTTS/text_to_stream.py:1136
↓ 1 callers
Method
_register_dll_directories
(self, directories: list[Path])
RealtimeTTS/engines/moss_tts_engine.py:311
↓ 1 callers
Method
_relative_position_to_absolute_position
x: [b, h, l, 2*l-1] ret: [b, h, l, l]
example_rvc/rvc/infer/lib/infer_pack/attentions.py:325
↓ 1 callers
Method
_resolve_backbone_repo
Prefer a cached local GGUF file to avoid repeat HF metadata calls.
RealtimeTTS/engines/neutts_engine.py:121
↓ 1 callers
Method
_resolve_cache_dir
(self, voice_cache_dir: Optional[str])
RealtimeTTS/engines/pocket_gpu_engine.py:109
↓ 1 callers
Method
_resolve_inline_action
Resolves a tag to an inline action if one is registered.
RealtimeTTS/text_to_stream.py:1084
↓ 1 callers
Method
_safe_cache_stem
(path: str)
RealtimeTTS/engines/zipvoice_engine.py:220
↓ 1 callers
Method
_same_padding
(self, x)
example_rvc/rvc/infer/lib/infer_pack/attentions.py:446
↓ 1 callers
Method
_save_voice_state
(self, voice_state: dict[str, Any], state_path: Path)
RealtimeTTS/engines/pocket_gpu_engine.py:267
↓ 1 callers
Method
_set_active_voice
Switches the engine voice and stores the current active mapping.
RealtimeTTS/text_to_stream.py:1127
↓ 1 callers
Method
_stationary_mask
Computes a stationary binary mask to filter out noise in a log-magnitude spectrogram. Arguments: X_db (torch.Tensor): 2D
example_rvc/rvc/tools/torchgate/torchgate.py:128
↓ 1 callers
Method
_synthesis_chunk_generator
Generates synthesis chunks based on buffered audio length. The function buffers chunks of synthesis until the buffered audio seconds
RealtimeTTS/text_to_stream.py:1185
↓ 1 callers
Method
_synthesize_on_worker
(self, text: str, sentence_count: int = 0)
RealtimeTTS/engines/pocket_engine.py:255
↓ 1 callers
Method
_synthesize_onnx
(self, text: str)
RealtimeTTS/engines/moss_tts_engine.py:504
↓ 1 callers
Method
_synthesize_onnx_text_chunk
(self, text: str, prompt_audio_codes)
RealtimeTTS/engines/moss_tts_engine.py:452
↓ 1 callers
Method
_synthesize_streaming
(self, text: str, ref_codes, ref_text: str)
RealtimeTTS/engines/neutts_engine.py:305
↓ 1 callers
Method
_synthesize_streaming
(self, text: str, start_time: float)
RealtimeTTS/engines/pocket_engine.py:496
↓ 1 callers
Method
_synthesize_torch
(self, text: str)
RealtimeTTS/engines/moss_tts_engine.py:532
↓ 1 callers
Method
_to_float_mono
(self, wav)
RealtimeTTS/engines/soprano_engine.py:125
↓ 1 callers
Method
_to_float_mono
(self, wav)
RealtimeTTS/engines/chatterbox_engine.py:165
↓ 1 callers
Method
_to_float_mono
(self, wav)
RealtimeTTS/engines/sopro_engine.py:212
↓ 1 callers
Method
_to_numpy_audio
(self, audio: Any)
RealtimeTTS/engines/pocket_gpu_engine.py:348
↓ 1 callers
Method
_voice_cache_key
(self, audio_path: str, transcript: str)
RealtimeTTS/engines/neutts_engine.py:242
↓ 1 callers
Method
_voice_cache_key
( self, voice_name: str, audio_path: Optional[str], state_path: Optional[str],
RealtimeTTS/engines/pocket_gpu_engine.py:210
↓ 1 callers
Method
_voice_to_api_payload
(self)
RealtimeTTS/engines/cartesia_engine.py:137
↓ 1 callers
Method
_warmup
Pre‑captures CUDA graphs by running a dummy synthesis. Uses the sentinel key to hit the cached embedding.
RealtimeTTS/engines/faster_qwen_engine.py:224
↓ 1 callers
Method
abort
(self)
tests/multilang_test_textual.py:661
↓ 1 callers
Method
accumulated_text
Retrieve the accumulated text from the iterated tokens.
RealtimeTTS/threadsafe_generators.py:182
↓ 1 callers
Method
add_pause
Registers a pause tag with a default silence duration in seconds. Args: tag (str): Tag content without delimiters, for e
RealtimeTTS/text_to_stream.py:346
↓ 1 callers
Method
add_voice
Add and optionally pre-encode a reference voice.
RealtimeTTS/engines/neutts_engine.py:391
↓ 1 callers
Function
align_wave_head_and_tail
(a, b)
example_rvc/rvc/infer/lib/uvr5_pack/lib_v5/spec_utils.py:200
↓ 1 callers
Method
apply_fade_in
Applies a linear fade-in over fade_duration_ms at the start of the audio.
RealtimeTTS/engines/base_engine.py:71
↓ 1 callers
Method
apply_fade_out
Applies a linear fade-out over fade_duration_ms at the end of the audio.
RealtimeTTS/engines/base_engine.py:85
↓ 1 callers
Function
apply_mask
(self, x, padding_mask, target_list)
example_rvc/rvc/infer/lib/jit/get_hubert.py:226
↓ 1 callers
Function
arg_parse
()
example_rvc/rvc/tools/infer_cli.py:19
↓ 1 callers
Function
arg_parse
()
example_rvc/rvc/tools/infer_batch_rvc.py:18
↓ 1 callers
Method
arg_parse
()
example_rvc/rvc/configs/config.py:70
↓ 1 callers
Function
arrange
(s, e, length, keep_length)
example_rvc/rvc/infer/lib/jit/get_hubert.py:166
↓ 1 callers
Function
async_producer
()
RealtimeTTS/engines/orpheus_decoder.py:123
↓ 1 callers
Function
async_token_gen
()
RealtimeTTS/engines/orpheus_decoder.py:119
↓ 1 callers
Method
attention
( self, query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, m
example_rvc/rvc/infer/lib/infer_pack/attentions.py:230
↓ 1 callers
Function
attention_init
()
example_rvc/rvc/infer/modules/ipex/attention.py:204
↓ 1 callers
Function
audio2
(i, o, format, sr)
example_rvc/rvc/infer/lib/audio.py:33
↓ 1 callers
Method
audio_callback
Core of the real-time processing - called for every block of audio data captured from the microphone - handles incoming audio
example_rvc/rvc/realtimervc.py:204
↓ 1 callers
Function
audio_chunk_generator
Yields audio chunks from the queue as they become available. This function is used by the StreamingResponse.
docker/zipvoice/serve_zipchunks.py:102
↓ 1 callers
Method
audio_chunk_generator
(self, send_wave_headers)
docker/openai-tts-docker/app/main.py:82
↓ 1 callers
Method
audio_chunk_generator
Generate audio chunks, converting format if necessary. Collects all audio, detects format, converts if needed, then creates a complet
example_fast_api/async_server.py:230
↓ 1 callers
Function
base64ToArrayBuffer
(base64)
example_fast_api/static/tts.js:103
↓ 1 callers
Function
benchmark
( model, inputs_path, device=torch.device("cpu"), epoch=1000, is_half=False )
example_rvc/rvc/infer/lib/jit/__init__.py:20
↓ 1 callers
Function
build_emotion_entries
()
tests/faster_qwen_emotions.py:75
↓ 1 callers
Function
build_system_prompt
()
tests/camb_test.py:49
↓ 1 callers
Function
cache_harvest_f0
(input_audio_path, fs, f0max, f0min, frame_period)
example_rvc/rvc/infer/modules/vc/pipeline.py:30
↓ 1 callers
Function
cal_cross_attn
(to_q, to_k, to_v, rand_input)
example_rvc/rvc/tools/calc_rvc_model_similarity.py:13
↓ 1 callers
Method
change_key
(self, new_key)
example_rvc/rvc/tools/rvc_for_realtime.py:200
↓ 1 callers
Function
change_rms
(data1, sr1, data2, sr2, rate)
example_rvc/rvc/infer/modules/vc/pipeline.py:43
↓ 1 callers
Function
check_and_install_packages
Checks if the specified packages are installed, and if not, prompts the user to install them. Parameters: - packages: A list of dict
tests/install_packages.py:5
↓ 1 callers
Method
cleanup
Cleanup audio resources
example_fast_api/websocket_client.py:166
↓ 1 callers
Method
clear_buffer
Clears all audio data from the buffer.
RealtimeTTS/stream_player.py:373
↓ 1 callers
Function
clear_console
()
tests/translator.py:40
↓ 1 callers
Method
close_stream
Closes the audio stream.
RealtimeTTS/stream_player.py:321
↓ 1 callers
Method
coarse_f0
(self, f0)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe.py:56
↓ 1 callers
Method
coarse_f0
(self, f0)
example_rvc/rvc/infer/modules/train/extract/extract_f0_print.py:95
↓ 1 callers
Method
coarse_f0
(self, f0)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe_dml.py:54
↓ 1 callers
Method
compute_f0
(self, path, f0_method)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe.py:42
↓ 1 callers
Method
compute_f0
(self, path, f0_method)
example_rvc/rvc/infer/modules/train/extract/extract_f0_print.py:44
↓ 1 callers
Method
compute_f0
(self, path, f0_method)
example_rvc/rvc/infer/modules/train/extract/extract_f0_rmvpe_dml.py:40
↓ 1 callers
Method
compute_f0
input: wav:[signal_length] p_len:int output: f0:[signal_length//hop_length]
example_rvc/rvc/infer/lib/infer_pack/modules/F0Predictor/F0Predictor.py:2
↓ 1 callers
Method
connect_and_test
Connect to WebSocket and send text messages
example_fast_api/websocket_client.py:25
↓ 1 callers
Function
convert_audio_to_pcm
Convert audio data from various formats to raw PCM. Returns: (pcm_data, sample_rate, channels, sample_width)
example_fast_api/server.py:90
↓ 1 callers
Function
convert_to_audio
(multiframe, count)
RealtimeTTS/engines/orpheus_decoder.py:16
↓ 1 callers
Function
create_complete_wav_file
Create a complete WAV file with proper headers and data.
example_fast_api/server.py:139
↓ 1 callers
Function
create_directories
()
example_rvc/download_models.py:15
↓ 1 callers
Method
create_engine
(self, name, language)
tests/multilang_test_textual.py:452
↓ 1 callers
Function
create_synthesis_callbacks
(start_time)
tests/kokoro_test.py:65
↓ 1 callers
Function
create_synthesis_callbacks
(start_time)
tests/coqui_test.py:20
↓ 1 callers
Function
create_wave_header_for_engine
(engine)
docker/openai-tts-docker/app/main.py:135
↓ 1 callers
Method
demix
(self, mix)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:109
↓ 1 callers
Method
demix_base
(self, mixes, margin_size)
example_rvc/rvc/infer/modules/uvr5/mdxnet.py:143
↓ 1 callers
Function
detect_audio_format
Detect audio format from the first few bytes of a chunk. Returns: 'mp3', 'wav', 'ogg', or 'pcm'
example_fast_api/server.py:65
↓ 1 callers
Method
device_config
(self)
example_rvc/rvc/configs/config.py:151
↓ 1 callers
Function
discriminator_loss
(disc_real_outputs, disc_generated_outputs)
example_rvc/rvc/infer/lib/train/losses.py:15
↓ 1 callers
Method
dl_model
(self, link, model_name, dir_name)
example_rvc/rvc/realtimervc.py:422
↓ 1 callers
Method
download_file
(url, destination)
RealtimeTTS/engines/coqui_engine.py:970
↓ 1 callers
Function
dummy_generator
()
tests/modelslab_test.py:24
↓ 1 callers
Function
dummy_generator
()
tests/simple_test.py:4
↓ 1 callers
Function
dummy_generator
()
tests/neutts_test.py:8
↓ 1 callers
Function
dummy_generator
()
tests/complex_test.py:45
↓ 1 callers
Function
dummy_generator
()
tests/openai_test.py:4
← previous
next →
301–400 of 1,468, ranked by callers