https://github.com/jina-ai/executor-coquitts

Executor that leverages CoquiTTS engine for text2speech
https://github.com/jina-ai/executor-coquitts

coqui tts

Last synced: about 2 months ago
JSON representation

Executor that leverages CoquiTTS engine for text2speech

• Host: GitHub
• URL: https://github.com/jina-ai/executor-coquitts
• Owner: jina-ai
• Created: 2022-02-24T18:18:34.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2022-03-15T12:42:42.000Z (almost 3 years ago)
• Last Synced: 2023-03-03T21:46:40.053Z (almost 2 years ago)
• Topics: coqui, tts
• Language: Python
• Homepage: https://hub.jina.ai/executor/2l3hglrc
• Size: 17.6 KB
• Stars: 2
• Watchers: 23
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# CoquiTTS

Executor that leverages CoquiTTS engine for text2speech

## Usage

- Put your text into `Document.text`;

- Send multiple Documents into a `DocumentArray`;

- Executors will generate speech from your text and store it in `.uri` as Data URI (namely, something starts with `data:audio/wav;`)

- You can use this embedded audio in HTML. Or directly play it in Jupyter Notebook.

```python

returned_da = ...

returned_da[0].display()

```

![img.png](img.png)

## Sandbox

The following code can be copy-paste and run in **Jupyter Notebook/Colab** as-is:

```python

from jina import Flow, Document

f = Flow().add(uses='jinahub+sandbox://CoquiTTS7')

with f:

    r = f.post('/', Document(text='hi Alex, are you near your laptop?'))

    r[0].display()

```