levantando la app text2speech con gradio

requirements.txt

@@ -0,0 +1,90 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==4.2.2
+anyio==3.6.2
+async-timeout==4.0.2
+attrs==22.2.0
+certifi==2022.12.7
+charset-normalizer==3.0.1
+click==8.1.3
+combo-lock==0.2.4
+contourpy==1.0.7
+cycler==0.11.0
+entrypoints==0.4
+fastapi==0.92.0
+ffmpy==0.3.0
+filelock==3.9.0
+fonttools==4.38.0
+frozenlist==1.3.3
+fsspec==2023.1.0
+gradio==3.19.0
+gTTS==2.3.1
+h11==0.14.0
+httpcore==0.16.3
+httpx==0.23.3
+huggingface-hub==0.12.1
+idna==3.4
+importlib-resources==5.12.0
+Jinja2==3.1.2
+json-database==0.7.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+kthread==0.2.3
+langcodes==3.3.0
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.2
+matplotlib==3.7.0
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+memory-tempfile==2.2.3
+multidict==6.0.4
+mycroft-messagebus-client==0.10.1
+neon-tts-plugin-coqui==0.7.2
+numpy==1.24.2
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+orjson==3.8.6
+ovos-backend-client==0.0.6
+ovos-config==0.0.5
+ovos-plugin-manager==0.0.21
+ovos-utils==0.0.27
+packaging==23.0
+pandas==1.5.3
+pexpect==4.8.0
+Pillow==9.4.0
+pkgutil_resolve_name==1.3.10
+psutil==5.9.4
+ptyprocess==0.7.0
+pycryptodome==3.17
+pydantic==1.10.5
+pydub==0.25.1
+pyee==8.1.0
+pyparsing==3.0.9
+pyrsistent==0.19.3
+pytesseract==0.3.10
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2022.7.1
+PyYAML==5.4.1
+quebra-frases==0.3.7
+requests==2.28.2
+rfc3986==1.5.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.25.0
+toolz==0.12.0
+torch==1.13.1
+tqdm==4.64.1
+typing_extensions==4.5.0
+uc-micro-py==1.0.1
+urllib3==1.26.14
+uvicorn==0.20.0
+watchdog==2.2.1
+websocket-client==1.5.1
+websockets==10.4
+yarl==1.8.2
+zipp==3.14.0

text2speech.py

@@ -0,0 +1,20 @@
+import tempfile
+import gradio as gr
+import pytesseract
+from gtts import gTTS
+
+def text_to_speech(inputs):
+	text = inputs
+	speech = gTTS(text)
+	speech.save("prueba.mp3")
+	return "prueba.mp3", text
+
+
+outputs = [gr.Audio(label="Output"), "text"]
+
+demo = gr.Interface(fn=text_to_speech, 
+             inputs="text",
+             outputs=outputs,
+             )
+             
+demo.launch()