zach commited on
Commit
633a175
·
1 Parent(s): 2192d9b

Update README

Browse files
Files changed (2) hide show
  1. README.md +9 -8
  2. src/static/audio/.gitkeep +0 -0
README.md CHANGED
@@ -2,13 +2,15 @@
2
  <img src="https://storage.googleapis.com/hume-public-logos/hume/hume-banner.png">
3
  <h1>Expressive TTS Arena</h1>
4
  <p>
5
- <strong> An web application for comparing and evaluating the expressiveness of different text-to-speech models </strong>
6
  </p>
7
  </div>
8
 
9
  ## Overview
10
 
11
- Expressive TTS Arena is an open-source web application that enables users to compare text-to-speech outputs with a focus on expressiveness rather than just audio quality. Built with [Gradio](https://www.gradio.app/), it provides a seamless interface for generating and comparing speech synthesis from different providers, including Hume AI and ElevenLabs.
 
 
12
 
13
  ## Prerequisites
14
 
@@ -87,18 +89,17 @@ Expressive TTS Arena/
87
 
88
  4. Test the application by navigating to the the localhost URL in your browser (e.g. `localhost:7860` or `http://127.0.0.1:7860`)
89
 
90
- 5. (Optional) If contributing, install pre-commit hook for automatic file formatting:
91
  ```sh
92
  uv run pre-commit install
93
  ```
94
 
95
  ## User Flow
96
 
97
- 1. **Choose or enter a character description**: Select a sample from the list or enter your own to guide text and voice generation.
98
- 2. **Generate text**: Click **"Generate Text"** to create dialogue based on the character. The generated text will appear in the input field automatically—edit it if needed.
99
- 3. **Synthesize speech**: Click **"Synthesize Speech"** to send your text and character description to two TTS APIs. Each API generates a voice and synthesizes speech in that voice.
100
- 4. **Listen & compare**: Play both audio options and assess their expressiveness.
101
- 5. **Vote for the best**: Click **"Select Option A"** or **"Select Option B"** to choose the most expressive output.
102
 
103
  ## License
104
 
 
2
  <img src="https://storage.googleapis.com/hume-public-logos/hume/hume-banner.png">
3
  <h1>Expressive TTS Arena</h1>
4
  <p>
5
+ <strong> A web application for comparing and evaluating the expressiveness of different text-to-speech models </strong>
6
  </p>
7
  </div>
8
 
9
  ## Overview
10
 
11
+ Expressive TTS Arena is an open-source web application for evaluating the expressiveness of voice generation and speech synthesis from different text-to-speech providers, including Hume AI and Elevenlabs.
12
+
13
+ For support or to join the conversation, visit our [Discord](https://discord.com/invite/humeai).
14
 
15
  ## Prerequisites
16
 
 
89
 
90
  4. Test the application by navigating to the the localhost URL in your browser (e.g. `localhost:7860` or `http://127.0.0.1:7860`)
91
 
92
+ 5. (Optional) If contributing, install pre-commit hook for automatic linting, formatting, and type-checking:
93
  ```sh
94
  uv run pre-commit install
95
  ```
96
 
97
  ## User Flow
98
 
99
+ 1. Select a sample character, or input a custom character description and click **"Generate Text"**, to generate your text input.
100
+ 2. Click the **"Synthesize Speech"** button to synthesize two TTS outputs based on your text and character description.
101
+ 3. Listen to both audio samples to compare their expressiveness.
102
+ 4. Vote for the most expressive result by clicking either **"Select Option A"** or **"Select Option B"**.
 
103
 
104
  ## License
105
 
src/static/audio/.gitkeep DELETED
File without changes