cverse-tts-inference-adapter v0.1.0

adapter

capsule://quake0day/[email protected]

Provides adapters for various Text-to-Speech (TTS) models, allowing the core inference service to generate speech using different providers (e.g., OpenAI TTS, Qwen TTS) through a unified interface.

Owns

Base TTS plugin interface
Specific TTS model implementations (e.g., OpenAI, Qwen)

Does not own

The core inference service
Other AI model types (ASR, LLM, Avatar, etc.)

AI orientation

An AI agent working on this capsule would focus on adding new TTS model integrations, improving speech synthesis quality, or optimizing the TTS plugin's interaction with external APIs. It requires knowledge of TTS technologies and Python plugin development.

Avoid

Modifying the core inference service or other AI model types.

Provides

library:tts-plugin — TTS model implementations conforming to the inference core's plugin interface.

Dependencies

Capsules

cverse-inference-core >=0.1.0

Invariants (must always hold)

TTS plugins must correctly convert text to audio.
Plugins must adhere to the defined TTS plugin interface.

Source files (4)

Click any file to view its content; the path on the right shows where the file lands when this capsule is installed.

src/inference/plugins/tts/__init__.py → plugins/tts/__init__.py
src/inference/plugins/tts/base.py → plugins/tts/base.py
src/inference/plugins/tts/openai_tts_plugin.py → plugins/tts/openai_tts_plugin.py
src/inference/plugins/tts/qwen_tts_plugin.py → plugins/tts/qwen_tts_plugin.py

Plus capsule.yaml and install.json.

Upstream source

https://github.com/quake0day/cyberverse-capsules/blob/main/cverse-tts-inference-adapter/capsule.yaml

Pull this capsule locally:

capsule pull capsule://quake0day/[email protected]

Or render to your terminal:

capsule man capsule://quake0day/[email protected]