v0.4.7

• updated requirements.txt, minor Readme updates

v0.4.6

• fix for #139
• implements #136 (thanks to https://github.com/criminact)

v0.4.5

• upgrade to use the latest libraries of all TTS provider engines
• added some parameters to play method:

  context_size_look_overhead (int)

  • Default: 12
  • Description: Additional context size for looking ahead when detecting sentence boundaries.

  fast_sentence_fragment_allsentences (bool)

  • Default: False
  • Description: When set to True, applies the fast sentence fragment processing to all sentences, not just the first one.

  fast_sentence_fragment_allsentences_multiple (bool)

  • Default: False
  • Description: When set to True, allows yielding multiple sentence fragments instead of just a single one.

v0.4.4

Added:

tokenize_sentences (callable)
- Default: None
- Description: A custom function that tokenizes sentences from the input text. You can provide your own lightweight tokenizer if you are unhappy with nltk and stanza. It should take text as a string and return split sentences as a list of strings.

and

before_sentence_synthesized (callable)
- Default: None
- Description: Callback function that gets called before a single sentence fragment gets synthesized.

Merged PR #109 (async server to serve multiple requests in parallel, thx to Raj Hammeer Singh Hada for providing this

v0.4.2

• support for customized installations
• upgraded version numbers of dependent libraries raised to latest versions
• fixed #96: expanded python_requires to include Python 3.12 (now '>=3.9, <3.13')

❗️ Please use pip install realtimetts[all] instead of pip install realtimetts now.

To install RealtimeTTS with support for all TTS engines:

pip install -U realtimetts[all]

Custom Installation

RealtimeTTS allows for custom installation with minimal library installations. Here are the options available:

• all: Full installation with every engine supported.
• system: Includes system-specific TTS capabilities (e.g., pyttsx3).
• azure: Adds Azure Cognitive Services Speech support.
• elevenlabs: Includes integration with ElevenLabs API.
• openai: For OpenAI voice services.
• gtts: Google Text-to-Speech support.
• coqui: Installs the Coqui TTS engine.
• minimal: Installs only the base requirements with no engine (only needed if you want to develop an own engine)

Say you want to install RealtimeTTS only for local neuronal Coqui TTS usage, then you should use:

pip install realtimetts[coqui]

If for example you want to install RealtimeTTS with only Azure Cognitive Services Speech, ElevenLabs, and OpenAI support:

pip install realtimetts[azure,elevenlabs,openai]

Virtual Environment Installation

For those who want to perform a full installation within a virtual environment, follow these steps:

python -m venv env_realtimetts
env_realtimetts\Scripts\activate.bat
python.exe -m pip install --upgrade pip
pip install -U realtimetts[all]

v0.4.1

• added emotions to azure engine
• added speed parameter to GTTSEngine (usage see gtts_test.py)
• switched coquiengine to Idiap Research Institute's maintained fork of coqui tts (thanks!)
• bugfix for ElevenlabsEngine get_voices method

v0.4.0

• New engine: GTTSEngine

  Offers realtime support for Google Translate's text-to-speech API (GTTS): free TTS without need for a GPU with a better sound quality than system voices can offer

  💖 Shoutout to Pierre Nicolas Durette for making this possible

v0.3.48

• switched to new elevenlabs api

v0.3.46

• fixed for #53 and #80

v0.3.45

• resolved an issue where feeding str content while still playing caused problems.
  Huge shoutout to Yokopops for pointing me to this bug, which was completely under the radar for me.
• fixed #75 (muted flag did not work for the ElevenlabsEngine)
• adjusted on_playback_start callback so that it's called before the first chunk plays instead of after