Subtitle to audio, generate audio/speech from any subtitle file using Coqui-ai TTS and synchronize the audio timing according to subtitle time.
Demo :
ffmpeg, pydub, librosa, coqui-ai TTS, ffmpeg-python
pip install TTS
pip install git+https://github.com/bnsantoso/sub-to-audiopip install TTS
pip install subtoaudioffmpeg on linux
apt-get install ffmpegBasic use is very similiar to Coqui-ai TTS, you can check their documentation and the <lang-iso_code>.
!Note: Use non-overlapping subtitles with an optimal Character per Second / CPS for best result
!Note: Use software like aegisub to edit your subtitle
from subtoaudio import SubToAudio
# list all model
SubToAudio().coqui_model()
# get model index
model = SubToAudio().coqui_model()[1]
# The code will output 'yoursubtitle.wav' in the current directory.
sub = SubToAudio(model_name=model)
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle)
# you can choose 1100 different language using fairseq model
sub = SubToAudio(fairseq_language='<lang-iso_code>')
subtitle = sub.subtitle("yoursubtitle.ass")
sub.convert_to_audio(sub_data=subtitle)
# specify model name
sub = SubToAudio(model_name="tts_models/multilingual/multi-dataset/your_tts")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, output_path="subtitle.wav")
# specify model and config path
sub = SubToAudio(model_path="path/to/your/model.pth" config_path="config/path.json")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle)
# speaker=tts.speakers[0] or None if model doesnt have multiple speakers
# language=tts.languages[0] or None if doesnt have multiple languages
# list speaker
sub.speakers()
speaker1 = sub.speakers()[1]
# list languages
sub.languages()
langu = sub.languages()[0]
sub = SubToAudio(model_name="tts_models/multilingual/multi-dataset/your_tts")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, language=langu, speaker=speaker1, output_path="subtitle.wav")
# Save temporary audio to current folder
sub = SubToAudio(model_name="tts_models/multilingual/multi-dataset/your_tts")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, output_path="subtitle.wav", save_temp=True)To use voice conversion method, you must pass voice_conversion:bool and speaker_wav:str paramater on self.convert_to_audio. Voice conversion cannot run if your model have multiple speakers.
from subtoaudio import SubToAudio
sub = SubToAudio(fairseq_language="eng")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, voice_conversion=True, speaker_wav="voice.wav", language="en")To use Coqui Studio Api you'll need to configure the COQUI_STUDIO_TOKEN environment variable.
import os
os.environ['COQUI_STUDIO_TOKEN'] = # yourapiAfter your token set you can get coqui studio model, you can follow this name convention coqui_studio/en/<studio_speaker_name>/coqui_studio
from subtoaudio import SubToAudio
sub = SubToAudio(model_name="coqui_studio/en/Torcull Diarmuid/coqui_studio", progress_bar=False)
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, output_path="subtitle.wav", save_temp=True)
# use emotion paramater and speed paramater
sub.convert_to_audio(sub_data=subtitle, output_path="subtitle.wav", emotion="Happy", speed=1.5)Use the tempo_mode parameter to speed up the audio. There are three tempo modes:
tempo_mode="all": This accelerates all audio. Usetempo_speed=floatto specify the speed.tempo_mode="overflow": This accelerates the audio to match the total subtitle duration plus the blank duration before the next subtitle appears.'tempo_limit'will limit the speed increase during overflow.tempo_mode="precise": This accelerates the audio to match the duration the subtitle appears."
from subtoaudio import SubToAudio
# Speed up tempo or speech rate
sub = SubToAudio(model_name="tts_models/de/thorsten/tacotron2-DDC")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="all", tempo_speed=1.3)
# Change the tempo or speech rate of all audio files , default is 1.2
sub = SubToAudio("tts_models/multilingual/multi-dataset/xtts_v1")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="all", tempo_speed=1.3)
# Change tempo or speech rate to audio that doesn't match the subtitle duration
sub = SubToAudio(fairseq_language="ind")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="overflow")
# Limit tempo speed on the overflow mode
sub = SubToAudio(fairseq_language="ind")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="overflow", tempo_limit=1.2)
# Match audio length to subtitle duration
sub = SubToAudio(fairseq_language="ind")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="precise")shift_mode parameter will shift audio that doesnt match subtitle duration.
shift_mode="right": Shift audio time to the right and prevent audio overlaping.shift_mode="left": Shift audio to the left and prevent audio overlap, but be cautious of limited space on the left side, as some audio may disappear.shift_mode="interpose": Shift audio to mid position and prevent right and left of audio overlaping. (Note: This mode can be clunky, so use it cautiously.)shift_mode="left-overlap": Shift audio time to the left, allowing overlap.shift_mode="interpose-overlap": Shift audio to mid position, allowing overlap.shift_limit=int or "str": limit audio shift, use integer for millisecond or string like2.5sfor second
from subtoaudio import SubToAudio
# shift mode with limit of 2 second to the right.
sub = SubToAudio(fairseq_language="vie")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=sub, tempo_mode="overflow", shift_mode="right", limit_shift="2s")
# shift audio to left position or, time before next subtitle appear
sub = SubToAudio(fairseq_language="fra")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=sub, shift_mode="left-overlap")
# shift to left, and limit shift only 1 sec.
sub = SubToAudio(fairseq_language="ind")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=sub, shift_mode="left", shift_limit=1000) # 1000 = 1sfrom subtoaudio import SubToAudio
# Random Speaker will give you weird result when using bark model with SubToAudio
# Bark random
sub = SubToAudio("tts_models/multilingual/multi-dataset/bark")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="overflow")
# Tortoise random
sub = SubToAudio("tts_models/en/multi-dataset/tortoise-v2")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, shift_mode="overflow", preset="fast")
# To use voice clone you need voice_dir and speaker paramater
# Voice Clone expecting .wav or .npz file inside folder speaker_1
# voice/speaker_1/hana.wav or voice/speaker_1/hana.npz
# if your speaker folder only have .wav file, it will generate .npz file after you runing it.
sub = SubToAudio("tts_models/multilingual/multi-dataset/bark")
subtitle = sub.subtitle("yoursubtitle.srt")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="overflow", voice_dir="voice/",speaker="speaker_1")
# same with bark, the folder structure like this 'voice/speaker2/ron.wav'
sub = SubToAudio("tts_models/en/multi-dataset/tortoise-v2")
subtitle = sub.subtitle("yoursubtitle.ass")
sub.convert_to_audio(sub_data=subtitle, tempo_mode="overflow", voice_dir="voice/", speaker="speaker2")Eren, G., & The Coqui TTS Team. (2021). Coqui TTS (Version 1.4) [Computer software]. https://doi.org/10.5281/zenodo.6334862
