qwen3-tts-voicedesign
von xiaoyaner0201
Coding Agents & IDEsKurzbeschreibung
Text-to-speech with Qwen3-TTS VoiceDesign.
Beschreibung
Was dieser Skill macht
Qwen3-TTS VoiceDesign converts text to speech using natural language voice descriptions combined with seed-based timbre control. The same description and seed pair always produces the same voice, enabling reproducible custom voices. Ships with an OpenAI-compatible HTTP server, one-click setup, and batch seed exploration scripts.
Seed-based timbre fixation means the same description and seed pair always reproduces the exact same voice, unlike most TTS APIs where voice consistency depends on proprietary speaker IDs.
Wann du ihn einsetzt
- Generating voiceovers for videos with a consistent custom voice
- Adding local TTS to an OpenClaw agent via OpenAI-compatible endpoint
- Exploring voice timbres by batch-testing dozens of random seeds
- Producing Chinese-language speech with specific accents or broadcast styles
- Self-hosting a TTS API to avoid third-party cloud service dependencies
Beispiel-Workflow
User asks: generate a deep male broadcaster voice saying 'Welcome to the news'
- 1
Set TTS_INSTRUCT to a description like '30岁男性播音员,声音低沉磁性,语速稳重从容'
- 2
Run batch_seeds.sh to generate samples across 30-40 seeds
- 3
Listen to samples and shortlist 2-3 candidates
- 4
Set the chosen seed as TTS_SEED in .env
- 5
Call say.sh with the input text to produce the final audio file
An MP3 file of 'Welcome to the news' spoken in the selected broadcaster voice
Voraussetzungen
- NVIDIA CUDA GPU with 4GB+ VRAM
Installation
clawhub install xiaoyaner0201/qwen3-tts-voicedesignFühre den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.