# KoljaB/RealtimeTTS

Converts text to speech in realtime

Repository: https://github.com/KoljaB/RealtimeTTS
Canonical: https://ross.abutalabs.com/products/realtimetts
Language: Python
License: MIT
License Family: permissive
Topics: python, realtime, speech-synthesis, text-to-speech
Last push: 2026-08-21T01:49:49+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 78
- inputs: {"age_days": 1103, "days_push": 13, "days_rel": 13, "gap_med": 5.5, "n_releases_24m": 37}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4016, forks 404 (observed 2026-08-28T04:08:32.419744+00:00)

## What it is
RealtimeTTS is a Python library that converts text, generators, and LLM token streams into speech audio with low latency. It supports multiple engines including local system voices, cloud APIs, local neural models, and voice cloning, with playback, streaming, and WAV file output.

## Use cases
- speak llm responses aloud as tokens stream in
- add realtime voice output to a python chatbot
- convert text to speech with low latency
- clone a voice for tts in python
- stream tts audio to another process
- write synthesized speech to wav files

## When to choose
- you need low-latency streaming TTS in Python, especially for LLM voice assistants
- you want to switch between local, cloud, and voice-cloning TTS engines behind one API

## When to avoid
- you need offline batch synthesis of large documents rather than streaming playback
- you need a non-Python environment or unsupported platform like macOS for the native Qwen engine

## Facets
- artifact type: library
- maturity: active
- function: tts, audio-processing, streaming
- domain: speech-processing, artificial-intelligence
- platform: python, windows
- tags: text-to-speech, realtime, voice-cloning, llm-streaming, low-latency, audio, linux, macos

## Member repositories
- KoljaB/RealtimeTTS (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:32.419744+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:58.310452+00:00, confidence not recorded.
  - readme: https://github.com/KoljaB/RealtimeTTS (fetched 2026-08-28T04:08:32.419744+00:00, sha f1fe48c262b5)
  - registry_pypi: https://pypi.org/pypi/realtimetts/json (fetched 2026-08-29T09:16:43.131441+00:00, sha 48523dd62fd1)
- Data as of 2026-08-30T08:39:29.467469+00:00.