0.4.2

jlumbroso/passage-of-time-mcp0.4.2May 19, 2025by edwko

AI Summary

Introduced batched and single-stream decoding interfaces, added fade-in/fade-out audio decoding, and added support for the OuteTTS 1.0 0.6B model.

Key Highlights

Fade-in/fade-out audio decoding to eliminate clipping artifacts
Batched decoding interfaces (EXL2 Async, VLLM, llama.cpp Async Server)
Single-stream decoding endpoint for llama.cpp
OuteTTS 1.0 0.6B model support
New batched interface parameters

New Features

Fade-in/fade-out audio decoding
Batched decoding interfaces
Single-stream decoding
OuteTTS 1.0 0.6B model support

Full Release Notes

# OuteTTS v0.4.2

* **Fade-in / Fade-out Audio Decoding**
  Introduced quick fade-in and fade-out on decoded audio chunks to eliminate clipping artifacts at segment boundaries.

* **Batched Decoding Interfaces**
  Added support for high-throughput, batched inference via three new backends:

  * **EXL2 Async**: Asynchronous batch processing using the EXL2.
  * **VLLM**: Asynchronous batch decoding with VLLM. (Experiment support)
  * **llama.cpp Async Server Endpoint**: Connects to a continuously-batched llama.cpp server for async inference.

* **Single-Stream Decoding**

  * **llama.cpp Server Endpoint**: single-stream decode endpoint for llama.cpp server.

* **OuteTTS 1.0 0.6B Model Support**
  Compatibility with the new [OuteTTS-1.0-0.6B](https://huggingface.co/OuteAI/OuteTTS-1.0-0.6B), including config defaults.

* **Batched Interface Parameters**
  New configuration options to control batched interface.

* Enhanced pre-prompt normalization pipeline.

* Documentation Updates, expanded the batched interface usage.