Gemini 3.8 Flash TTS API: AI 音频生成

通过 Muapi REST API 使用 Gemini 3.8 Flash TTS生成音频。按次生成付费，无需订阅。

交互式模型控制

Gemini 3.8 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with studio-grade voice fidelity, expressive acting, and long-form stability. Control voice, accent, emotional style, and pace per speaker for fast, affordable voiceovers, character dialogue, and narration.

Gemini 3.8 Flash TTS API 文档

端点

POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts

使用 Muapi API 密钥在 x-api-key 请求头中提交任务，然后轮询 https://api.muapi.ai/api/v1/predictions/{request_id}/result 直到状态变为 completed。

参数

名称	类型	必填	描述
speakers	array	是	说话人声音配置列表。每一轮对话通过 ID 引用一个说话人。
dialogue_turns	array	是	按顺序排列的对话行列表。每一轮的 speaker_id 必须匹配上面定义的说话人。文本可以包含 [shouting] 或 [whispers] 等语气标签。
scene	string	否	可选的 scene description that sets the acoustic setting, e.g. "A quiet, warm room with a fireplace crackling softly."默认值: ""
sample_context	string	否	可选的 overall tone/style, e.g. "Audiobook style narration. Tone is gentle and inviting."默认值: ""
temperature	number	否	采样温度（0-2）。数值越高，表达方式越丰富。默认值: 1

cURL 示例

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"speakers":[],"dialogue_turns":[]}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python 示例

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/gemini-3-8-flash-tts", headers=headers, json={"speakers":[],"dialogue_turns":[]})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

完整文档及 Agent/MCP 集成： llms.txt. 在此获取 API 密钥： muapi.ai/access-keys.