curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"voice": "Rachel",
"speed": 1.08,
"stability": 0.55,
"similarity_boost": 0.78,
"style": 0.12,
"timestamps": false,
"apply_text_normalization": "auto",
"text": "Welcome to NovaDesk. Your workspace is ready, your calendar is synced, and your first customer briefing starts in ten minutes."
}
}
'{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2026-06-25T10:30:00"
}
}{
"code": 200,
"error": {
"message": "<string>",
"type": "<string>"
}
}{
"code": 200,
"error": {
"message": "<string>",
"type": "<string>"
}
}ElevenLabs
ElevenLabs TTS Turbo v2.5
ElevenLabs TTS Turbo v2.5 API 可将最多 40,000 个字符的文本转换为语音，支持选择音色、0.7 到 1.2 的语速，以及可选的 ISO 639-1 语言代码。可传入前文和后文，使多个请求之间的旁白保持连贯。
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"voice": "Rachel",
"speed": 1.08,
"stability": 0.55,
"similarity_boost": 0.78,
"style": 0.12,
"timestamps": false,
"apply_text_normalization": "auto",
"text": "Welcome to NovaDesk. Your workspace is ready, your calendar is synced, and your first customer briefing starts in ten minutes."
}
}
'{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2026-06-25T10:30:00"
}
}{
"code": 200,
"error": {
"message": "<string>",
"type": "<string>"
}
}{
"code": 200,
"error": {
"message": "<string>",
"type": "<string>"
}
}- 提交后会返回
task_id。如果提供了callback_url，当任务状态变为finished或failed时，系统会向callback_url发送 POST 请求。 - 无论是否提供
callback_url，都可以通过统一的查询任务状态接口获取结果。
elevenlabs-tts-turbo-2-5 将文本输入转换为低延迟的多语言语音音频。结果以任务 files 返回，与图像、视频、3D 和音频任务的标准响应结构一致。
模型
- elevenlabs-tts-turbo-2-5 - ElevenLabs TTS Turbo v2.5 文本转语音生成
必填参数
- text：要转换为语音的文本
- 长度：
1-40000个字符 - 将长篇旁白拆分为多个请求时，使用
previous_text和next_text
- 长度：
可选参数
- voice：用于语音生成的音色名称或兼容的音色 ID。默认：
Rachel - stability：音色稳定性，
0到1。默认：0.5 - similarity_boost：音色相似度增强，
0到1。默认：0.75 - style：风格夸张程度，
0到1。默认：0 - speed：语速，
0.7到1.2。默认：1 - timestamps：布尔值。为
true时，生成的音频可能附带时间戳数据 - previous_text：可选，位于
text之前的上下文，有助于保持长篇内容连贯 - next_text：可选，位于
text之后的上下文，有助于保持长篇内容连贯 - language_code：可选的 ISO 639-1 代码，用于强制指定目标语言，例如
en、fr、de、ja、vi、hu或no - apply_text_normalization：
auto、on或off。默认：auto
示例
低延迟产品配音
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"text": "Welcome to NovaDesk. Your workspace is ready, your calendar is synced, and your first customer briefing starts in ten minutes.",
"voice": "Rachel",
"speed": 1.08,
"stability": 0.55,
"similarity_boost": 0.78,
"style": 0.12,
"timestamps": false,
"apply_text_normalization": "auto"
}
}
本地化取货通知
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"text": "Bonjour, votre commande est prete. Merci de presenter votre code de retrait a l'accueil.",
"voice": "Aria",
"language_code": "fr",
"stability": 0.6,
"similarity_boost": 0.75,
"speed": 1,
"timestamps": true,
"apply_text_normalization": "auto"
}
}
长篇内容连贯
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"previous_text": "The city lights faded behind the train.",
"text": "Mira lowered her voice and said, keep the map close. By sunrise, everyone will be looking for it.",
"next_text": "The carriage fell silent as the tunnel opened ahead.",
"voice": "Sarah",
"stability": 0.42,
"similarity_boost": 0.82,
"style": 0.35,
"speed": 0.94,
"apply_text_normalization": "auto"
}
}
富有表现力的主持人开场
{
"model": "elevenlabs-tts-turbo-2-5",
"callback_url": "https://your-domain.com/callback",
"input": {
"text": "Tonight, the gallery opens with a quiet piano note, then the host welcomes every guest with calm confidence.",
"voice": "Laura",
"stability": 0.48,
"similarity_boost": 0.8,
"style": 0.4,
"speed": 0.98,
"apply_text_normalization": "auto"
}
}
注意事项
- PoYo 对外公开的参数名是
text。 - 通过标准任务状态 API 查询状态。
- 成功响应返回
files，其中生成的语音使用file_type: audio。
授权
所有 API 接口都需要 Bearer Token 认证。
创建 API Key：登录 PoYo，进入 仪表盘 → API 密钥（poyo.ai/zh/dashboard/api-key），点击创建 Key。
在请求头中添加：
Authorization: Bearer YOUR_API_KEY
请求体
application/json
响应
任务提交成功
Show child attributes
Show child attributes