0.4.2

antgroup/echomimic_v20.4.2May 19, 2025by edwko

AI Summary

OuteTTS v0.4.2 introduces batched decoding interfaces, audio fade-in/out effects, and support for the OuteTTS 1.0 0.6B model.

Key Highlights

Implemented Fade-in/Fade-out audio decoding to prevent clipping
Added batched decoding interfaces (EXL2, VLLM, llama.cpp)
Added support for OuteTTS 1.0 0.6B model
Enabled single-stream decoding for llama.cpp server

New Features

Fade-in/Fade-out audio effects
Batched decoding backends
OuteTTS 1.0 0.6B model compatibility
Enhanced pre-prompt normalization
Expanded batched interface documentation

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.