google/gemini-3.8-flash-lite-tts

文档
Schema

[Core Function] Gemini 3.8 Flash Lite TTS is Google's text-to-speech model for low-latency speech generation. [Strengths] Single-speaker synthesis, two-speaker dialogue, 101 languages, per-turn style control, and WAV output (24 kHz mono PCM). [Best For] Bulk narration, voice-agent responses, read-aloud features, and multilingual dialogue. [Limitations] Do NOT use this for streaming, voice creation, music generation, or audio, image, or video input. Dialogue requires exactly two speakers with prebuilt or extended-library voices; designed or replicated voices are limited to single-speaker synthesis. Combined text and style must stay within 8,192 Unicode characters. [Routing] Choose Flash Lite for latency and cost efficiency; choose Gemini 3.8 Flash TTS for expressive delivery and broader language coverage.

$24.2500/M chars$12.1250/M chars
text-to-speech

输入

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 delivery direction for single-speaker synthesis. Not spoken aloud.
Verbatim transcript. Required for single-speaker synthesis.
Required for single-speaker synthesis. Prebuilt voice name, extended voice-library ID, or a designed/replicated voice ID (voice_... or voicekey_...). No spaces.
Exactly two speakers for dialogue. Use with turns.
第 1 项
speaker*

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

voice*

Prebuilt voice name or extended voice-library ID, such as Puck or Kore. Designed or replicated voices (voice_... or voicekey_...) are not supported in dialogue. No spaces.

第 2 项
speaker*

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

voice*

Prebuilt voice name or extended voice-library ID, such as Puck or Kore. Designed or replicated voices (voice_... or voicekey_...) are not supported in dialogue. No spaces.

Dialogue turns in order. Each speaker must match a name in speakers, case-sensitively.
第 1 项
speaker*

Which configured speaker says this turn.

style

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

text*

Verbatim line for this turn.

结果

暂无结果

运行模型后，结果将在这里显示。

Next:

README

属性

参数

参数名 描述 类型 必填 枚举值
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 否 -
style Optional delivery direction for single-speaker synthesis. Not spoken aloud. string 否 -
text Verbatim transcript. Required for single-speaker synthesis. string 否 -
voice Required for single-speaker synthesis. Prebuilt voice name, extended voice-library ID, or a designed/replicated voice ID (voice_… or voicekey_…). No spaces. string 否 -
speakers Exactly two speakers for dialogue. Use with turns. object[] 否 -
turns Dialogue turns in order. Each speaker must match a name in speakers, case-sensitively. object[] 否 -

价格

输入图片（$/img）: 0.0000
输入视频（$/sec）: 0.0000

单位: $/M chars

价格
$12.1250/M chars