Gemini 3.1 Flash TTS API Examples for PoYo

Focused server-side examples for building expressive text-to-speech workflows with Gemini 3.1 Flash TTS on PoYo.

Gemini 3.1 Flash TTS is useful for expressive narration, multi-speaker dialogue drafts, audio tags, product voiceovers, and creator-tool speech generation.

Try on PoYo | Get API Key | Docs | Pricing | Main Examples

What This Repo Covers

• Text-to-speech with gemini-3-1-flash-tts
• Style instructions and voice control
• Output format selection
• Async task flow with polling and webhooks
• cURL and Node.js backend examples

Quick Start

cp .env.example .env
export POYO_API_KEY="your-api-key"

Run the Node.js example:

cd node
npm start

Keep POYO_API_KEY on the server. Do not expose it in browser code, mobile apps, screenshots, or public logs.

Production Pattern

• Keep POYO_API_KEY on the server
• Submit a generation task
• Store data.task_id
• Poll status while testing
• Use callback_url webhooks in production

Models

This repo uses gemini-3-1-flash-tts.

Examples

Path	What it covers
curl/generate.md	Copy-paste API request.
node/	Native Node.js backend example.
docs/prompt-examples.md	Practical prompts for product workflows and creative tests.
docs/production-notes.md	Security and reliability notes before launch.
webhooks/express-webhook/	Minimal Express receiver for PoYo callbacks.

Run Checks

make check

On Windows:

./scripts/check.ps1

License

MIT