Gemini 3.8 Flash TTS API 呼叫參考
富有表現力的語音，能演出 [laughing] 這類提示
只要一把 PopNow API 金鑰，就能在自己的程式裡呼叫 Gemini 3.8 Flash TTS。以下列出要填的呼叫名稱、這個型號接受的每個輸入欄位、每次請求花多少點數，以及一段可以直接貼進終端機執行的請求。
參數說明直接取自型號的輸入 schema，目前只有英文。
總覽
- 開發商
- 產出
- 音訊
- 起價
- 0.05 點 每秒成片 ($0.0005)
- 一般耗時
- 約 11 秒
1 點 = 0.01 美元。任務受理時會先保留可能的最高費用，完成後依實際用量結算、無條件進位到整點，多保留的會退回；失敗的任務不扣點數。想在執行前知道確切數字，請先呼叫 POST /api/v1/jobs/quote。
文字轉語音
google/gemini-3.8-flash-tts/text-to-speech
價格
| 選項 | 點數 (每秒成片) | 美元 |
|---|---|---|
預設 | 0.05 | $0.0005 |
參數
| 欄位 | 型別 | 預設值 | 可用值 | 用途 |
|---|---|---|---|---|
text選填 | string | — | 最多 5000 個字元 | The words to be spoken, exactly as written. Direction such as [whispering] or [sighs] goes into the text itself. |
dialogue選填 | array<object> | — | 最多 20 項 | A scripted conversation, used instead of text: each line names a speaker from speakers. |
speakers選填 | array<object> | — | 最多 2 項 | The cast for dialogue: one or two voices, each with a name the lines refer to. |
voice_id選填 | string | Kore | Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, … (+16) | Prebuilt voice that reads the text. Each voice has a fixed character. |
style選填 | string | — | whisper, empathetic, vocal_smile, newscaster, promo_hype, deadpan | Overall manner of the reading. Omit it to use the voice's own default manner. |
pace選填 | string | — | natural, rapid_fire, the_drift, staccato | Rhythm of the reading. Omit it to keep the voice's own rhythm. |
accent選填 | string | — | neutral, american_general, american_valley, american_south, british_rp, british_brixton, transatlantic, australian | English accent used for the reading. |
instructions選填 | string | — | 最多 1000 個字元 | How to read the text: mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken. |
scene選填 | string | — | 最多 500 個字元 | Where and to whom the words are spoken. Shapes the delivery and is not spoken. |
temperature選填 | number | — | 0 到 2 | Variation between takes; higher is less predictable. |
請求範例
這段請求原樣就能執行，沒寫的欄位都用預設值。執行前請先把金鑰放進環境變數 POPNOW_API_KEY。
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask?wait=60" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "google/gemini-3.8-flash-tts/text-to-speech",
"input": {
"text": "Hi there! This voice was created with the PopNow API in just a few seconds."
}
}'回應會立刻帶回 taskId。之後用 GET /api/v1/jobs/recordInfo 取得結果，或在請求裡加上 callBackUrl 等候通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"