🔥 Black Friday AI API deals are live· New drops every MondayEnds in--d --:--:--See deals →
muapi Logomuapi Logo
muapi Logomuapi Logo

Gemini 3.8 Flash TTS: AI音声・音楽生成

Generate expressive multi-speaker speech with Gemini 3.8 Flash TTS. Studio-grade voice fidelity and long-form stability. Try free, pay per use. Gemini 3.8 Flash TTS is Google's newer-generation text-to-speech model, built for studio-grade voice fidelity, expressive acting, and long-form stability. Define any number of speakers, each with a distinct voice, accent, emotional style, and pace, then script a conversation across ordered dialogue turns with inline tone tags like [whispers] or [shouting]. It is ideal for character dialogue, game and video voiceovers, podcasts, and narration where you need natural, expressive delivery at speed. For even lower latency and cost on high-volume workloads, see Gemini 3.8 Flash Lite TTS; for premium studio-quality output, see Gemini 2.5 Pro TTS.

インタラクティブなモデルコントロール

Generate expressive multi-speaker speech with Gemini 3.8 Flash TTS. Studio-grade voice fidelity and long-form stability. Try free, pay per use.

📝

概要

このモデルについて

Gemini 3.8 Flash TTS is Google's newer-generation text-to-speech model, built for studio-grade voice fidelity, expressive acting, and long-form stability. Define any number of speakers, each with a distinct voice, accent, emotional style, and pace, then script a conversation across ordered dialogue turns with inline tone tags like [whispers] or [shouting]. It is ideal for character dialogue, game and video voiceovers, podcasts, and narration where you need natural, expressive delivery at speed. For even lower latency and cost on high-volume workloads, see Gemini 3.8 Flash Lite TTS; for premium studio-quality output, see Gemini 2.5 Pro TTS.

1Games & Interactive: Voice NPCs and branching dialogue with distinct, emotionally-directed characters.
2Video & Shorts: Generate expressive, studio-grade voiceovers and character lines for content production.
3Podcasts: Produce multi-host conversational audio from a written script.
4Prototyping: Iterate quickly on tone, accent, and pacing before a final high-fidelity render.
💰

料金と価値

コスト分析

muapiapp$0.015 1,000文字あたり

生成ごとのお支払いで、サブスクリプション不要。Google公式の Gemini 3.8 Flash TTS 音声出力料金に準じています。

Fal.ai利用不可

このモデルは提供されていません。

Replicate利用不可

このモデルは提供されていません。

** 競合サービスの料金は類似のモデル構成および利用ティアに基づいて算出された推定値です。

⚙️

技術詳細

設定スキーマ

Speakersarray

音声合成で使用する話者または声のキャラクター識別子。

デフォルト値[object Object],[object Object]
Dialogue Turnsarray

音声合成で使用する話者または声のキャラクター識別子。

デフォルト値[object Object],[object Object],[object Object],[object Object]
Scenestring

Optional scene description that sets the acoustic setting, e.g. "A quiet, warm room with a fireplace crackling softly."

デフォルト値
Sample Contextstring

Optional overall tone/style, e.g. "Audiobook style narration. Tone is gentle and inviting."

デフォルト値
温度（創造性）number

サンプリングのランダム性を制御する温度パラメータ。高い値ほど創造的な出力になります。

デフォルト値1
📖

実装ガイド

開発者ドキュメント

How to Use Gemini 3.8 Flash TTS

  1. Define your speakers: Add one entry per voice to the speakers list. Give each a speaker_id in "Speaker N" format, pick a voice_name, and set the accent, style, and pace. Optionally add an audio_profile describing the persona.

  2. Write the dialogue: Fill dialogue_turns with ordered lines. Each turn's speaker_id must match a speaker you defined. You can embed tone tags inline such as [whispers], [shouting], or [determination].

  3. Set the mood (optional): Use scene to describe the acoustic setting and sample_context to set the overall narration tone. Adjust temperature (0-2) for more or less varied delivery.

  4. Submit and poll: POST the request, then poll /predictions/{request_id}/result until the status is completed to get the audio URL.

curl -X POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "speakers": [
      {"speaker_id": "Speaker 1", "voice_name": "Fenrir", "accent": "British (RP)", "style": "Deadpan", "pace": "Natural"},
      {"speaker_id": "Speaker 2", "voice_name": "Puck", "accent": "American (Gen)", "style": "Empathetic", "pace": "Staccato"}
    ],
    "dialogue_turns": [
      {"speaker_id": "Speaker 1", "text": "[shouting] Halt, traveler!"},
      {"speaker_id": "Speaker 2", "text": "[determination] I carry a message for the elder."}
    ],
    "scene": "A dark, crumbling dungeon.",
    "temperature": 1
  }'
❓

よくある質問

FAQ

How do I create a multi-speaker conversation?

Define each voice in the `speakers` list with a unique `speaker_id` (in "Speaker N" format), then reference those IDs in your `dialogue_turns`. The model renders each line in that speaker's assigned voice, accent, style, and pace.

Can I control emotion and pacing?

Yes. Each speaker has `style` (Vocal Smile, Newscaster, Whisper, Empathetic, Promo/Hype, Deadpan) and `pace` (Natural, Rapid Fire, The Drift, Staccato) settings. You can also embed inline tone tags like [whispers], [shouting], or [determination] directly in the dialogue text.

What voices and accents are available?

There are 30 prebuilt voices (Zephyr, Fenrir, Puck, Kore, and more) and 8 accents including Neutral, American variants, British (RP), British (Brixton), Transatlantic, and Australian.

How is pricing calculated?

Pricing is based on the total number of characters across all dialogue turns, at $0.015 per 1,000 characters — matching Google's official Gemini 3.8 Flash TTS audio-output rate. You pay per generation with no subscription.

What is the maximum length per line?

Each dialogue turn's text can be up to 10,000 characters. You can include multiple turns to build longer conversations.

How does this differ from Gemini 3.1 Flash TTS and Gemini 3.8 Flash Lite TTS?

Gemini 3.8 Flash TTS is Google's newer generation Flash tier, tuned for studio-grade voice fidelity, expressive acting, and long-form stability at a lower cost than the 3.1 line. Gemini 3.8 Flash Lite TTS trades a little fidelity for even lower latency and cost on high-throughput, conversational workloads.