360 Secure SkillHub
360 安全技能中心

Poyo Gemini 3 1 Flash Tts

该技能用于PoYo平台的Gemini 3.1 Flash TTS语音生成，核心功能含单/双Speaker合成，可配置风格指令、音色预设、多语言等参数，支持异步任务提交、状态查询，还能提供curl示例。典型场景：用户有该模型语音生成需求或需构建相关工作流。输入需必填文本，可选风格、音色等参数；输出含任务ID、参数汇总及后续操作指引，需注意POYO_API_KEY的安全管理。

coolhackboy
coolhackboy
热度 30.45
最近更新 2026-07-09 10:50:46
分类：创作依赖：第三方 API / 代码执行应用场景：API 集成 / 自动化脚本 / 文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add poyo-gemini-3-1-flash-tts
Metadata
name
poyo-gemini-3-1-flash-tts
description
Generate speech on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `gemini-3-1-flash-tts`, Gemini text-to-speech, style instructions, voice presets, language code, two-speaker dialogue, output formats, async task submission, callbacks, and task status retrieval.
metadata
{"openclaw":{"homepage":"https://poyo.ai/models/gemini-3-1-flash-tts","requires":{"bins":["curl"],"env":["POYO_API_KEY"]},"primaryEnv":"POYO_API_KEY"}}

PoYo Gemini 3.1 Flash TTS

PoYo Links

Use this skill for gemini-3-1-flash-tts jobs on PoYo. It helps agents prepare text-to-speech payloads, choose single-speaker or two-speaker mode, submit async tasks, and explain result retrieval through PoYo task status.

Use When

  • The user mentions PoYo Gemini 3.1 Flash TTS, gemini-3-1-flash-tts, text-to-speech, style instructions, voice presets, audio tags, multilingual speech, or two-speaker dialogue.
  • The workflow needs a PoYo speech payload, async task submission, a callback URL, or task status retrieval guidance.
  • The user wants server-side curl or shell examples for PoYo speech generation.

Model Selection

  • gemini-3-1-flash-tts: use for PoYo text-to-speech generation with style instructions, voice presets, and optional two-speaker dialogue.

Key Inputs

  • text is required.
  • style_instructions can guide delivery, pace, accent, tone, or emotion.
  • voice selects a preset for single-speaker synthesis.
  • language_code can steer multilingual synthesis when supported.
  • speakers enables exactly two speakers; each speaker_id must match prefixes in text.
  • temperature controls delivery variation.
  • output_format can be mp3, wav, or ogg_opus.
  • callback_url is optional and useful for production queues.

Security Rules

  • Treat POYO_API_KEY as a secret.
  • Keep PoYo API keys in server-side environment variables or a backend secret manager.
  • Never place an API key in browser code, frontend bundles, public repositories, logs, screenshots, or chat output.
  • Do not make live API calls unless the user explicitly asks and provides a safe server-side environment.
  • Do not log private scripts, customer text, callback URLs, task ids, or generated audio URLs unless the product policy allows it.

Execution

  • Read references/api.md for endpoint details, request fields, examples, and result retrieval notes.
  • Use scripts/submit_gemini_3_1_flash_tts.sh only when the user wants to submit a prepared JSON payload from a trusted shell.
  • If the user only needs a curl example, adapt one from references/api.md.
  • After submission, report the returned task_id clearly so follow-up retrieval is easy.

Output Expectations

When helping with Gemini 3.1 Flash TTS, include:

  • chosen model id
  • single-speaker or two-speaker mode
  • voice presets and style instructions
  • final payload or concise parameter summary
  • returned task_id if a request was actually submitted
  • next step: query task status or wait for webhook