v0.8.6
SparkAudio/Spark-TTSv0.8.6Sep 20, 2026by KoljaB
Upgrading?
AI Summary
A RealtimeTTS release focused on adding Qwen model support, enhancing streaming capabilities, and improving portability.
Key Highlights
- Added Qwen GPU and CPU server installation extras.
- Implemented em-dash streaming and language detection.
- Added segment controls and CPU onset recovery.
New Features
- Qwen GPU and CPU server installation extras
- Em-dash streaming support
- Language detection
- Segment controls
- CPU onset recovery
Full Release Notes
Adds Qwen GPU and CPU server installation extras, restores tests/faster_qwen_emotions.py, and includes em-dash streaming, language detection, segment controls, and CPU onset recovery. The portable CPU build reproduced the Linux baseline audio; measured first-audio latency was 4.5–6.9 ms higher than the server-specific build, an accepted portability trade-off. See the installation documentation for supported platforms and requirements.
Related Repositories
public-apis/public-apis★ 491,128
A collective list of free APIs
NousResearch/hermes-agent★ 255,903
The agent that grows with you
yt-dlp/yt-dlp★ 200,002
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,481
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,700
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.