Upload 4 files

.gitignore

@@ -0,0 +1,5 @@
+venv
+.idea
+*.pyc
+*.iml
+*.wav

app.py

@@ -0,0 +1,19 @@
+import gradio as gr
+
+from coqui_tts import CoquiTTS
+
+
+def speech(text, audio):
+    coqui_tts = CoquiTTS(speaker_wave_file = audio)
+    return coqui_tts.speech_text_and_save_it(text, "output.wav")
+
+
+interface = gr.Interface(
+    fn = speech,
+    inputs = [gr.Textbox(placeholder = "Your text to speech here"),
+              gr.Audio(sources = ["microphone"], type = "filepath")],
+    outputs = [gr.Audio(label = "File path")]
+    , allow_flagging = "never")
+
+if __name__ == '__main__':
+    interface.launch()

coqui_tts.py

@@ -0,0 +1,15 @@
+import torch
+from TTS.api import TTS
+
+
+class CoquiTTS:
+    def __init__(self, speaker_wave_file):
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(self.device)
+        self.speaker_wave_file = speaker_wave_file
+
+    def speech_text_and_save_it(self, text, output_path, language = "en"):
+        return self.tts.tts_to_file(text = text,
+                                    speaker_wav = self.speaker_wave_file,
+                                    language = language,
+                                    file_path = output_path)

requirements.txt

@@ -0,0 +1,216 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.8
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyascii==0.3.2
+anyio==4.6.2.post1
+argbind==0.3.9
+asttokens==3.0.0
+async-timeout==5.0.1
+attrs==24.2.0
+audioread==3.0.1
+babel==2.16.0
+bangla==0.0.2
+blinker==1.9.0
+blis==0.7.11
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.7
+cachetools==5.5.0
+catalogue==2.0.10
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.4.0
+click==8.1.7
+cloudpathlib==0.20.0
+confection==0.1.5
+contourpy==1.2.1
+coqpit==0.0.17
+cycler==0.12.1
+cymem==2.0.10
+Cython==3.0.11
+dateparser==1.1.8
+decorator==4.4.2
+descript-audiotools==0.7.2
+distro==1.9.0
+docopt==0.6.2
+docstring_parser==0.16
+einops==0.8.0
+encodec==0.1.1
+exceptiongroup==1.2.2
+executing==2.1.0
+fastapi==0.115.4
+ffmpy==0.4.0
+filelock==3.16.1
+fire==0.7.0
+Flask==3.1.0
+flatten-dict==0.4.2
+fonttools==4.54.1
+frozenlist==1.5.0
+fsspec==2024.10.0
+future==1.0.0
+g2pkk==0.1.2
+google-api-core==2.23.0
+google-api-python-client==2.153.0
+google-auth==2.36.0
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.1
+googleapis-common-protos==1.63.1
+gradio==4.44.1
+gradio_client==1.3.0
+grpcio==1.68.0
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.1
+gruut-lang-en==2.0.1
+gruut-lang-es==2.0.1
+gruut-lang-fr==2.0.2
+h11==0.14.0
+hangul-romanize==0.1.0
+httpcore==1.0.6
+httplib2==0.22.0
+httpx==0.27.2
+huggingface-hub==0.26.2
+idna==3.10
+imageio==2.36.0
+imageio-ffmpeg==0.5.1
+importlib_metadata==8.5.0
+importlib_resources==6.4.5
+inflect==7.4.0
+ipython==8.18.1
+itsdangerous==2.2.0
+jamo==0.4.1
+jedi==0.19.2
+jieba==0.42.1
+Jinja2==3.1.4
+jiter==0.7.1
+joblib==1.4.2
+jsonlines==1.2.0
+julius==0.2.7
+kiwisolver==1.4.7
+langcodes==3.5.0
+language_data==1.3.0
+lazy_loader==0.4
+librosa==0.10.0
+llvmlite==0.43.0
+marisa-trie==1.2.1
+Markdown==3.7
+markdown-it-py==3.0.0
+markdown2==2.5.1
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+more-itertools==10.5.0
+moviepy==1.0.3
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.1.0
+murmurhash==1.0.11
+mutagen==1.47.0
+natsort==8.4.0
+networkx==2.8.8
+nltk==3.9.1
+num2words==0.5.13
+numba==0.60.0
+numpy==1.22.0
+oauthlib==3.2.2
+openai==1.55.0
+opencv-python==4.10.0.84
+orjson==3.10.10
+packaging==24.1
+pandas==1.5.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.3.0
+platformdirs==4.3.6
+pooch==1.8.2
+preshed==3.0.9
+proglog==0.1.10
+prompt_toolkit==3.0.48
+propcache==0.2.0
+proto-plus==1.25.0
+protobuf==3.19.6
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyloudnorm==0.1.1
+pynndescent==0.5.13
+pyparsing==3.2.0
+pypinyin==0.53.0
+pysbd==0.3.4
+pystoi==0.4.1
+python-crfsuite==0.9.11
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.16
+pytz==2024.2
+PyYAML==6.0.2
+randomname==0.2.1
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.9.3
+rsa==4.9
+ruff==0.7.1
+safetensors==0.4.5
+schedule==1.2.2
+scikit-learn==1.5.2
+scipy==1.11.4
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+smart-open==7.0.5
+sniffio==1.3.1
+soundfile==0.12.1
+soxr==0.5.0.post1
+spacy==3.7.5
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+stack-data==0.6.3
+starlette==0.41.2
+SudachiDict-core==20241021
+SudachiPy==0.6.9
+sympy==1.13.1
+tensorboard==2.18.0
+tensorboard-data-server==0.7.2
+termcolor==2.5.0
+thinc==8.2.5
+threadpoolctl==3.5.0
+tokenizers==0.20.3
+tomlkit==0.12.0
+torch==2.5.1
+torch-stoi==0.2.3
+torchaudio==2.5.1
+tqdm==4.66.6
+trainer==0.0.36
+traitlets==5.14.3
+transformers==4.46.3
+TTS==0.22.0
+typeguard==4.4.1
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+tzlocal==5.2
+umap-learn==0.5.7
+Unidecode==1.3.8
+uritemplate==4.1.1
+urllib3==2.2.3
+uvicorn==0.32.0
+wasabi==1.1.3
+wcwidth==0.2.13
+weasel==0.4.1
+websockets==12.0
+Werkzeug==3.1.3
+wrapt==1.17.0
+yarl==1.18.0
+zipp==3.20.2