google/gemini-3.8-flash-tts

ドキュメント
スキーマ

[Core Function] Gemini 3.8 Flash TTS is Google's controllable text-to-speech model, currently in Preview. [Strengths] Single-speaker and two-speaker dialogue, preset voices, 130 languages via language_code, and expressive delivery through turn-level style and inline vocal tags. Output is WAV (24 kHz mono PCM). [Best For] Voiceovers, audiobook narration, multilingual speech, podcast-style scripts, and two-person dialogue. [Limitations] Do NOT use this for streaming, voice creation, lip-syncing existing video, music or sound-effect generation, image or audio inputs, MP3/OGG export, or API-level speed, volume, encoding, or sample-rate controls. Dialogue requires exactly two speakers with preset voices. Combined text and style must stay within 8,192 Unicode characters. [Routing] Route here for expressive Gemini TTS with per-turn style control; for the prompt-based request format use Gemini 3.1 Flash TTS; for video with native audio use Veo.

$20.0000/M chars
text-to-speech

入力

Optional BCP-47 language tag in lowercase. Examples: en-us, cmn-cn, ja-jp. The model can also detect the language from the transcript.
Optional single-speaker delivery direction (emotion, pace, tone). Not spoken aloud. Max 8,192 characters, counted together with text.
Verbatim transcript for single-speaker synthesis. Required in single-speaker mode. Do not include stage directions here. Inline vocal events use angle brackets. Together with style, the request must stay within 8,192 characters.
Required for single-speaker synthesis. Prebuilt voice name, extended voice-library ID, or a designed/replicated voice ID (voice_... or voicekey_...). No spaces. Max 256 characters.
Required for two-speaker synthesis. Exactly two speakers. Omit this field for single-speaker calls.
項目 1
speaker*

Speaker name used by turns. Alphanumeric, 1-64 characters.

voice*

Preset Gemini voice name for this speaker, such as Puck or Kore. Designed or replicated voices (voice_... or voicekey_...) are not supported in dialogue.

項目 2
speaker*

Speaker name used by turns. Alphanumeric, 1-64 characters.

voice*

Preset Gemini voice name for this speaker, such as Puck or Kore. Designed or replicated voices (voice_... or voicekey_...) are not supported in dialogue.

Required for two-speaker synthesis. One object per spoken turn, in order. Each speaker must match a name in speakers, case-sensitively. All turns produce one WAV file. The sum of all turn text and trimmed style must stay within 8,192 Unicode characters.
項目 1
speaker*

Which configured speaker says this turn.

style

Optional delivery direction for this turn only. Not spoken aloud.

text*

Verbatim line for this turn.

結果

結果はまだありません

モデルを実行すると、ここで出力をプレビューできます。

次の操作：

README

属性

パラメーター

名前 説明 型 必須 列挙値
language_code Optional BCP-47 language tag in lowercase. Examples: en-us, cmn-cn, ja-jp. The model can also detect the language from the transcript. string いいえ -
style Optional single-speaker delivery direction (emotion, pace, tone). Not spoken aloud. Max 8,192 characters, counted together with text. string いいえ -
text Verbatim transcript for single-speaker synthesis. Required in single-speaker mode. Do not include stage directions here. Inline vocal events use angle brackets. Together with style, the request must stay within 8,192 characters. string いいえ -
voice Required for single-speaker synthesis. Prebuilt voice name, extended voice-library ID, or a designed/replicated voice ID (voice_… or voicekey_…). No spaces. Max 256 characters. string いいえ -
speakers Required for two-speaker synthesis. Exactly two speakers. Omit this field for single-speaker calls. object[] いいえ -
turns Required for two-speaker synthesis. One object per spoken turn, in order. Each speaker must match a name in speakers, case-sensitively. All turns produce one WAV file. The sum of all turn text and trimmed style must stay within 8,192 Unicode characters. object[] いいえ -

料金

入力画像（$/img）: 0.0000
入力動画（$/sec）: 0.0000

単位: $/M chars

料金
$20.0000/M chars