TeToS

A unified interface for multiple Text-to-Speech (TTS) providers.

Supported TTS providers

• Edge-TTS

• OpenAI TTS

  Required parameters:

  • api_key: OpenAI API key

• Azure TTS

  Required parameters(Please refer to the documentation to get the secrets):

  • speech_key: Azure Speech service key
  • speech_region: Azure Speech service region

• Google TTS

  Requirements:

  • Enable the Text-to-Speech API in the Google Cloud Console
  • Environment variables GOOGLE_APPLICATION_CREDENTIALS pointing to the service account key file

• Volcengine TTS(火山引擎)

  Required parameters:

  • access_key: Volcengine access key ID. (Get it here)
  • secret_key: Volcengine access secret key. (Get it here)
  • app_key: Volcengine app key

• Baidu TTS

  Required parameters:

  • api_key: Baidu API key
  • secret_key: Baidu secret key

  Get both at the console

• Minimax TTS

  Required parameters:

  • api_key: Minimax API key
  • group_id: Minimax group ID

  Get both at the Minimax console

Installation

Requires Python 3.8 or higher.

pip install tetos

CLI Usage

tetos PROVIDER [PROVIDER_OPTIONS] TEXT [--output FILE]

Please run tetos --help for available providers and options.

Examples

tetos google "Hello, world!"
tetos azure "Hello, world!" --output output.mp3   # save to another file
tetos edge --lang zh-CN "你好，世界！"  # specify language
tetos openai --voice echo "Hello, world!"  # specify voice

API Usage

Use Azure TTS as an example:

from tetos.azure import AzureSpeaker

speaker = AzureSpeaker(speech_key='...', speech_region='...')
speaker.say('Hello, world!', 'output.mp3')

The initialization parameters may be different for other providers.

Behind a proxy

TeTos respects the proxy environment variables HTTP_PROXY, HTTPS_PROXY, ALL_PROXY and NO_PROXY.

TODO

• Google TTS
• SSML support

License

Apache License 2.0