metadata
license: mit
language:
- en
pipeline_tag: text-to-speech
tags:
- audiocraft
- audiogen
- styletts2
- audio
- synthesis
- shift
- audeering
- dkounadis
- sound
- scene
- acoustic-scene
- audio-generation
Affective TTS / SoundScape
- SHIFT TTS tool with Affective voices
- Analysis of emotionality #1
- Soundscape
e.g. trees, water, hills,
, generation via AudioGen landscape2soundscape.py
shows how to overlay TTS & Soundscape to Images and create videos
Available Voices
API
Install
virtualenv --python=python3 ~/.envs/.my_env
source ~/.envs/.my_env/bin/activate
cd shift/
pip install -r requirements.txt
Flask
CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=2 python api.py
The following need api.py
to be running on a tmux session
.
Text 2 Speech
# Basic TTS - See Available Voices
python tts.py --text sample.txt --voice "en_US/m-ailabs_low#mary_ann" --affective
# voice cloning
python tts.py --text sample.txt --native assets/native_voice.wav
Image 2 Video
# Make video narrating an image - All above TTS args apply also here!
python tts.py --text sample.txt --image assets/image_from_T31.jpg
Video 2 Video
# Video Dubbing - from time-stamped subtitles (.srt)
python tts.py --text assets/head_of_fortuna_en.srt --video assets/head_of_fortuna.mp4
# Video narration - from text description (.txt)
python tts.py --text assets/head_of_fortuna_GPT.txt --video assets/head_of_fortuna.mp4
Landscape 2 Soundscape
# TTS & soundscape - overlay to .mp4
python landscape2soundscape.py
Examples
Substitute Native voice via TTS
Same video where Native voice is replaced with English TTS voice with similar emotion
Video dubbing from subtitles .srt
.srt
Video Dubbing
Generate dubbed video:
python tts.py --text assets/head_of_fortuna_en.srt --video assets/head_of_fortuna.mp4
Joint Application of D3.1 & D3.2
From an image and text create a video:
python tts.py --text sample.txt --image assets/image_from_T31.jpg
Landscape 2 Soundscape
- YouTube Videos
# Loads image & text & sound-scene text and creates .mp4
python landscape2soundscape.py
Live Demo - Paplay
Flask
CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=/data/dkounadis/.hf7/ CUDA_VISIBLE_DEVICES=4 python live_api.py
Client (Ubutu)
python live_demo.py # will ask text input & play soundscape