KeyoAPI

Gemini 3.8 Flash TTS API on KeyoAPI — Low-Latency Speech

Gemini 3.8 Flash TTS for controllable, low-latency speech on the same Keyo API key as chat — calls use Gemini-native generateContent, not the OpenAI-compatible /v1/audio/speech endpoint.

Listed price: ~$0.44 / $8.82 per 1M in/out · Confirm live on interactive pricing.

Open interactive pricing Compare API prices Create account

Overview

gemini-3.8-flash-tts is Gemini Flash text-to-speech on KeyoAPI. Indicative rates about $0.44 / $8.82 per 1M in/out — confirm live on the gemini-3.8-flash-tts Model Square page. Call POST /v1beta/models/gemini-3.8-flash-tts:generateContent with responseModalities ["AUDIO"] and receive WAV audio inline (base64) in the same response. Use IndexTTS-2 or CosyVoice3 when you already run async TTS jobs.

Quick start

Base URL: https://www.keyoapi.xyz/v1

Endpoint: POST /v1beta/models/gemini-3.8-flash-tts:generateContent

Model: model=gemini-3.8-flash-tts

curl https://www.keyoapi.xyz/v1beta/models/gemini-3.8-flash-tts:generateContent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Hello from Gemini 3.8 Flash TTS."}]}],"generationConfig":{"responseModalities":["AUDIO"],"speechConfig":{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}}}}'

Auth uses the same Bearer API key as chat. Full notes: Keyo docs.

FAQ

Sync or async?

Sync: the generateContent response carries inline WAV audio (base64) in candidates[0].content.parts. Async TTS on Keyo remains Qwen3-TTS / CosyVoice3.

Where is live pricing?

See /pricing/gemini-3.8-flash-tts. Indicative ~$0.44 / $8.82 per 1M in/out.

Related models

Gemini 3.8 Flash API IndexTTS-2 API CosyVoice3 API

Guide for gemini-3.8-flash-tts. Try/buy: the gemini-3.8-flash-tts Model Square page · Catalog: the pricing page.