Saltar al contenido
TakoAPI
Volver a skills

qwen3-tts-voicedesign

por xiaoyaner0201

Coding Agents & IDEs
305Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Text-to-speech with Qwen3-TTS VoiceDesign.

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

User asks: generate a deep male broadcaster voice saying 'Welcome to the news'

AGENTE
  1. 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. 2

    Run batch_seeds.sh to generate samples across 30-40 seeds

  3. 3

    Listen to samples and shortlist 2-3 candidates

  4. 4

    Set the chosen seed as TTS_SEED in .env

  5. 5

    Call say.sh with the input text to produce the final audio file

SALIDA

An MP3 file of 'Welcome to the news' spoken in the selected broadcaster voice

Requisitos

  • NVIDIA CUDA GPU with 4GB+ VRAM

Instalación

clawhub install xiaoyaner0201/qwen3-tts-voicedesign

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces