created basic text to speech app - first commit

.gitignore

@@ -0,0 +1,162 @@
+tts_openai_secrets.py
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.ipynb

@@ -0,0 +1,254 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3bedf0dc-8d8e-4ede-a9e6-b8f35136aa00",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#|default_exp app"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "667802a7-0f36-4136-a381-e66210b20462",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "#tts_openai_secrets.py content:\n",
+    "#import os\n",
+    "#os.environ['OPENAI_API_KEY'] = 'sk-XXXXXXXXXXXXXXXXXXXXXX'\n",
+    "try:\n",
+    "    import tts_openai_secrets\n",
+    "except:\n",
+    "    print('secret import from tts_openai_secrets.py failed - env var must be previously set')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d9863fc-969e-409b-8e20-b9c3cd2cc3e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "try:\n",
+    "    import nbdev\n",
+    "except:\n",
+    "    print('to convert this notebook to app.py you need to pip install nbdev')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f486d3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "import gradio as gr\n",
+    "import openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ffd33b4-cb9b-4c01-bff6-4c3102854ab6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['tts-1-hd', 'tts-1-hd-1106', 'canary-tts', 'tts-1', 'tts-1-1106']\n"
+     ]
+    }
+   ],
+   "source": [
+    "#| export\n",
+    "tts_models = [o.id for o in openai.models.list().data if 'tts' in o.id]\n",
+    "print(tts_models)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2ddbca5d-4b04-43ab-afaf-430802980e78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "tts_voices = ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4e3957f-b97a-4aee-933d-44bfba60b633",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "client = openai.OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5388e860",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "def create_speech(input_text, model='tts-1', voice='alloy'):\n",
+    "    response = client.audio.speech.create(\n",
+    "        model=model,\n",
+    "        voice=voice,\n",
+    "        input=input_text,\n",
+    "        speed=1.0\n",
+    "    )\n",
+    "    return response.content"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "236dd8d3-4364-4731-af93-7dcdec6f18a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "def get_input_text_len(input_text):\n",
+    "    return len(input_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4fb3159-579b-4271-bc96-4cd1e2816eca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "with gr.Blocks(title='OpenAI TTS', head='OpenAI TTS') as app:\n",
+    "    gr.Markdown(\"# OpenAI TTS\")\n",
+    "    gr.Markdown(\"Start typing below and then click **Go** to create the speech from your text. The current limit is 4,000 characters.\")\n",
+    "    with gr.Row():\n",
+    "        input_text = gr.Textbox(max_lines=100, label=\"Enter text here\")\n",
+    "    with gr.Row():\n",
+    "        tts_model_dropdown = gr.Dropdown(value='tts-1',choices=tts_models, label='Model')\n",
+    "        tts_voice_dropdown = gr.Dropdown(value='alloy',choices=tts_voices,label='Voice')\n",
+    "        input_text_length = gr.Label(label=\"Number of characters\")\n",
+    "        output_audio = gr.Audio()\n",
+    "    input_text.input(fn=get_input_text_len, inputs=input_text, outputs=input_text_length)\n",
+    "    go_btn = gr.Button(\"Go\")\n",
+    "    go_btn.click(fn=create_speech, inputs=[input_text, tts_model_dropdown, tts_voice_dropdown], outputs=[output_audio])\n",
+    "    clear_btn = gr.Button('Clear')\n",
+    "    clear_btn.click(fn=lambda: '', outputs=input_text)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb886d45",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://0.0.0.0:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://localhost:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#| export\n",
+    "app.launch()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "28e8d888-e790-46fa-bbac-4511b9ab796c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Closing server running on port: 7860\n"
+     ]
+    }
+   ],
+   "source": [
+    "#| hide\n",
+    "app.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "afbc9699-4d16-4060-88f4-cd1251754cbd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "gr.close_all()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0420310d-930b-4904-8bd4-3458ad8bdbd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "nbdev.export.nb_export('app.ipynb',lib_path='.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9869749d-bc7c-4e24-9dbc-403f665d6200",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "python3",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -0,0 +1,62 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
+
+# %% auto 0
+__all__ = ['tts_models', 'tts_voices', 'client', 'create_speech', 'get_input_text_len']
+
+# %% app.ipynb 1
+#tts_openai_secrets.py content:
+#import os
+#os.environ['OPENAI_API_KEY'] = 'sk-XXXXXXXXXXXXXXXXXXXXXX'
+try:
+    import tts_openai_secrets
+except:
+    print('secret import from tts_openai_secrets.py failed - env var must be previously set')
+
+# %% app.ipynb 3
+import gradio as gr
+import openai
+
+# %% app.ipynb 4
+tts_models = [o.id for o in openai.models.list().data if 'tts' in o.id]
+print(tts_models)
+
+# %% app.ipynb 5
+tts_voices = ['alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer']
+
+# %% app.ipynb 6
+client = openai.OpenAI()
+
+# %% app.ipynb 7
+def create_speech(input_text, model='tts-1', voice='alloy'):
+    response = client.audio.speech.create(
+        model=model,
+        voice=voice,
+        input=input_text,
+        speed=1.0
+    )
+    return response.content
+
+# %% app.ipynb 8
+def get_input_text_len(input_text):
+    return len(input_text)
+
+# %% app.ipynb 9
+with gr.Blocks(title='OpenAI TTS', head='OpenAI TTS') as app:
+    gr.Markdown("# OpenAI TTS")
+    gr.Markdown("Start typing below and then click **Go** to create the speech from your text. The current limit is 4,000 characters.")
+    with gr.Row():
+        input_text = gr.Textbox(max_lines=100, label="Enter text here")
+    with gr.Row():
+        tts_model_dropdown = gr.Dropdown(value='tts-1',choices=tts_models, label='Model')
+        tts_voice_dropdown = gr.Dropdown(value='alloy',choices=tts_voices,label='Voice')
+        input_text_length = gr.Label(label="Number of characters")
+        output_audio = gr.Audio()
+    input_text.input(fn=get_input_text_len, inputs=input_text, outputs=input_text_length)
+    go_btn = gr.Button("Go")
+    go_btn.click(fn=create_speech, inputs=[input_text, tts_model_dropdown, tts_voice_dropdown], outputs=[output_audio])
+    clear_btn = gr.Button('Clear')
+    clear_btn.click(fn=lambda: '', outputs=input_text)
+    
+
+# %% app.ipynb 10
+app.launch()

requirements.txt

@@ -0,0 +1,2 @@
+openai==1.3.5
+gradio==4.7.1