Back: Catalog

RealtimeTTS

RealtimeTTS is a Python library that converts text, manufacturers, and LLM token streams into audio with low latency. Local system sounds support a variety of audio engines, including cloud API and local neural models. You can play outputs directly, save them as WAV files, or transfer them to different processes.

RE

RealtimeTTS

New80

KoljaB · Voice & Text-to-Speech

STARS4.0K
FORKS414
COMMITS0
CONTRIBUTORS0
VERSIONv0.8.10
UPDATED2 days ago
PythonTTSSes SentezlemeDüşük GecikmeMIT

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can convert text sequences or LLM token streams to audio with low latency.
  • You can play the generated audio data locally or save it as a WAV file.
  • Using different sound engines like Qwen, you can synthesize sound cloning and multilingual speech.
User reviews
  • • NeutralGitHub Issue

    Stream audio to frontend JS in browser?

    “Hi, Is it possible to call this via frontend JS and then stream audio directly to browser for playback? If so, what should the approach be? Thank You!”

  • • NeutralGitHub Issue

    Support multiple langaues per engine

    “Can you make the same module support more than one language at the same time? For example: (GTTS engine) I can only pass language not a list of languages ``` def __init__(self, language: str = 'en', tld: str = 'com', chunk_length: int = 100, crossfade_length: int = 10,…”

GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech