Add application file

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Yixuan Wang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,14 +1,19 @@
----
-title: Openai Tts
-emoji: 🏢
-colorFrom: pink
-colorTo: pink
-sdk: gradio
-sdk_version: 5.3.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: A GUI to convert text to speech using OpenAI API
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# OpenAI TTS Gradio Interface
+
+This is a simple Gradio Interface to use OpenAI Text-to-Speech API. The interface looks like this:
+
+![Interface](interface.png)
+
+## Usage
+
+Get your OpenAI API key following the tutorial [here](https://platform.openai.com/docs/quickstart). I use [Miniforge](https://github.com/conda-forge/miniforge) to set up the environment, but you can use Anaconda or any other package manager.
+
+```bash
+mamba env create -f env.yaml # Create the environment
+conda activate openai_tts # Activate the environment
+python app.py # Run the app
+```
+
+## Acknowledgement
+
+This repo is adapted from [https://github.com/leokwsw/OpenAI-TTS-Gradio](https://github.com/leokwsw/OpenAI-TTS-Gradio)

app.py

@@ -0,0 +1,73 @@
+import os
+import sys
+from typing import Union, Literal
+
+import gradio as gr
+import tempfile
+
+from openai import OpenAI
+
+server_name = os.getenv("SERVER_NAME", "127.0.0.1")
+
+def tts(
+        text: str,
+        model: Union[str, Literal["tts-1", "tts-1-hd"]],
+        voice: Literal["alloy", "echo", "fable", "onyx", "nova", "shimmer"],
+        output_file_format: Literal["mp3", "opus", "aac", "flac"] = "mp3",
+        speed: float = 1.0,
+        openai_key: str = ""
+):
+    if len(text) > 0:
+        try:
+            client = OpenAI(api_key=openai_key)
+
+            response = client.audio.speech.create(
+                model=model,
+                voice=voice,
+                input=text,
+                response_format=output_file_format,
+                speed=speed
+            )
+
+        except Exception as error:
+            print(str(error))
+            raise gr.Error(
+                "An error occurred while generating speech. Please check your API key and come back try again.")
+
+        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_file:
+            temp_file.write(response.content)
+
+        temp_file_path = temp_file.name
+
+        return temp_file_path
+    else:
+        return "1-second-of-silence.mp3"
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# <center> OpenAI Text-To-Speech API with Gradio </center>")
+    with gr.Row(variant="panel"):
+        model = gr.Dropdown(choices=["tts-1", "tts-1-hd"], label="Model", value="tts-1")
+        voice = gr.Dropdown(choices=["alloy", "echo", "fable", "onyx", "nova", "shimmer"], label="Voice Options",
+                            value="alloy")
+        output_file_format = gr.Dropdown(choices=["mp3", "opus", "aac", "flac"], label="Output Options", value="mp3")
+        speed = gr.Slider(minimum=0.25, maximum=4.0, value=1.0, step=0.01, label="Speed")
+
+    openai_key = gr.Textbox(label="OpenAI API Key", placeholder="Enter your OpenAI API key")
+    text = gr.Textbox(label="Input text",
+                      placeholder="Enter your text and then click on the \"Text-To-Speech\" button, "
+                                  "or simply press the Enter key.")
+    btn = gr.Button("Text-To-Speech")
+    output_audio = gr.Audio(label="Speech Output")
+
+    text.submit(fn=tts, inputs=[text, model, voice, output_file_format, speed, openai_key], outputs=output_audio, api_name="tts")
+    btn.click(fn=tts, inputs=[text, model, voice, output_file_format, speed, openai_key], outputs=output_audio, api_name=False)
+
+demo.launch(server_name=server_name)
+
+# curl --location "http://127.0.0.1:7860/api/tts" \
+# --header "Content-Type: application/json" \
+# --data "{"data":["Hello", "tts-1", "alloy"]}"
+
+# curl --location "http://127.0.0.1:7860/file=/private/var/folders/5v/
+# 0b0l_t1x3752h3t1bt_rtnjr0000gn/T/gradio/e91d8bf36ee07f536bed6b5a5bf9522b1fc86436/tmpkem8ubvz.mp3"

env.yaml

@@ -0,0 +1,9 @@
+name: openai_tts
+channels:
+  - conda-forge
+dependencies:
+  - python=3.9
+  - pip=22.2.2
+  - pip:
+    - gradio==4.12.0
+    - openai==1.2.3