qwen3-tts-local-inference
par jithinm
DevOps & CloudRésumé
Generate speech from text using Qwen3-TTS via direct Python inference — no server required.
Description
Ce que fait ce skill
Runs Qwen3-TTS speech synthesis locally via Python with no server or API required. Supports three modes: built-in speakers, natural language voice description, and voice cloning from a short audio clip. Outputs .wav files and works fully offline after the initial model download.
Runs entirely offline after setup, avoiding API rate limits, per-character costs, and data privacy concerns tied to cloud TTS services.
Quand l'utiliser
- Generating voiceovers for video content without cloud costs
- Cloning a speaker's voice from a 3-second audio clip
- Producing multilingual audio narration in Chinese, English, Japanese, or Korean
- Embedding TTS generation directly into a Python data pipeline
- Quickly prototyping spoken UI with a specific emotional tone or accent
Exemple de workflow
User asks: clone my voice from a short recording and read back a script in English
- 1
Locate the reference audio file (~3 seconds) and its transcript
- 2
Run tts.py with --mode voice-clone, --ref-audio, --ref-text, and the target text
- 3
Monitor output for the generated .wav file path
- 4
Confirm duration and inference time from the JSON result
A .wav file in tts_output/ spoken in the cloned voice
Installation
clawhub install jithinm/qwen3-tts-local-inferenceExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.