Saltar al contenido
TakoAPI
Volver a skills

chichi-speech

por hudeven

Speech & Transcription
1.6kDescargas según clawskills.sh
1Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

A RESTful service for high-quality text-to-speech using Qwen3.

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

User asks: synthesize 'Nice to meet you' in English

AGENTE
  1. 1

    Start the chichi-speech server on port 9090 with a reference audio URL and reference text

  2. 2

    Confirm the service is healthy by hitting the /docs endpoint

  3. 3

    Send a POST request to /synthesize with the text and language fields

  4. 4

    Receive the synthesized audio as a WAV file

SALIDA

output/nice_to_meet.wav containing the cloned-voice speech

Requisitos

  • Reference audio file (URL or local path) for voice cloning if using a custom voice

Instalación

clawhub install hudeven/chichi-speech

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

Enlaces