Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Initial release of chichi-speech as an installable RESTful text-to-speech service. - Provides FastAPI-based service for high-quality TTS with Qwen3 and voice cloning via reference audio. - Command line interface (CLI) for easy server startup with customizable reference audio and text options. - Includes usage examples, service endpoint documentation, and cURL sample requests.
What This Skill Does
A FastAPI-based REST service that converts text to speech using the Qwen3 TTS model. Designed around voice cloning with a cached reference audio prompt, so the voice stays consistent and generation stays fast across requests.
Pre-computing the voice prompt from the reference audio avoids redundant inference on every request, making repeated synthesis faster than services that process the reference each time.
When to use it
- Converting written content to audio with a consistent cloned voice
- Running a local TTS endpoint for integration into other tools or scripts
- Testing voice cloning with custom reference audio files
- Generating speech in multiple languages via a simple HTTP call
- Embedding speech synthesis into an application via REST API
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: synthesize 'Nice to meet you' in English
- 1Start the chichi-speech server on port 9090 with a reference audio URL and reference text
- 2Confirm the service is healthy by hitting the /docs endpoint
- 3Send a POST request to /synthesize with the text and language fields
- 4Receive the synthesized audio as a WAV file
output/nice_to_meet.wav containing the cloned-voice speech
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.