跳到正文
TakoAPI
返回技能列表

fish-tts

由 gtank1 提供

DevOps & Cloud
421下载量由 clawskills.sh 提供
1星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

This skill uses **Fish Audio S1** to generate high-quality text-to-speech audio and upload it to NextCloud.

描述

该技能的功能

Converts text to speech using a self-hosted Fish Audio S1 instance and uploads the resulting MP3 to NextCloud via WebDAV. Supports multiple voices across languages and emotion tags for prosody control.

Combines TTS generation and cloud upload into a single scripted step, removing the need to manually transfer audio files after generation.

何时使用

  • Narrating daily notes and saving them to cloud storage
  • Generating voiceovers for video scripts with a specific voice style
  • Batch-producing audio files organized by date in NextCloud
  • Adding emotion-tagged speech to automated notification workflows
  • Testing different voices before committing to a long-form audio project

示例工作流

输入

User asks: generate an excited-tone greeting with af_sarah and upload it to NextCloud

智能体
  1. 1

    Select voice af_sarah and add [excited] emotion tag to input text

  2. 2

    POST request to Fish Audio S1 API with model, text, and voice parameters

  3. 3

    Save response audio to a temp MP3 file

  4. 4

    PUT the MP3 to NextCloud via WebDAV using NEXTCLOUD_USER and NEXTCLOUD_PASS

输出

MP3 file stored at /Openclaw/ on the NextCloud instance, timestamped filename confirmed

前置要求

  • Fish Audio S1 service running and accessible (FISH_AUDIO_S1_URL environment variable)
  • NEXTCLOUD_USER environment variable
  • NEXTCLOUD_PASS environment variable
  • NEXTCLOUD_URL environment variable
  • NextCloud instance with WebDAV enabled

安装

clawhub install gtank1/fish-tts

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接