- 语言大模型
- 图片生成
- 统一接口
- GPT-Image-1
- DALL.E
- Stability.ai
- Midjourney
- Midjourney-Relax
- 302.AI
- SDXL(图片生成)
- SDXL-Lora(图片生成-Lora)
- SDXL-Lightning(快速图片生成)
- SDXL-Lightning-V2(快速图片生成V2)
- SD3(图片生成-SD3)
- Aura-Flow(图片生成)
- Kolors(图片生成-可灵)
- Kolors(参考图片生成-可灵)
- QRCode(艺术二维码生成)
- Lora(图片生成-Lora)
- Lora(获取任务结果)
- SD-3.5-Large(图片生成)
- SD-3.5-Large-Turbo( 图片生成)
- SD-3.5-Medium(图片生成)
- Lumina-Image-V2(图片生成)
- Playground-v25(图片生成)
- Omnigen-V1(图片生成)
- Glif
- Flux
- Ideogram
- Recraft
- Luma
- Doubao即梦
- Minimax海螺
- 智谱
- Baidu百度
- Hidream
- Bagel
- 硅基流动
- Higgsfield
- 图片处理
- 302.AI-ComfyUI
- 302.AI
- Upscale(图片放大)
- Upscale-V2(图片放大V2)
- Upscale-V3(图片放大V3)
- Upscale-V4(图片放大V4)
- Super-Upscale(超级图片放大)
- Super-Upscale-V2(超级图片放大V2)
- Face-upscale(人像照片放大)
- Colorize(黑白照片上色)
- Colorize(黑白照片上色V2)
- Removebg(背景消除)
- Removebg-V2(背景消除V2)
- Removebg-V3(背景消除V3)
- Inpaint(图片修改)
- Erase(物体消除)
- Face-to-many(人像照片风格化)
- Llava(图像识别)
- Relight(二次打光)
- Relight-background(二次打光背景合成)
- Relight-V2(二次打光-V2)
- Face-swap-V2(AI换脸V2)
- Fetch(获取任务结果)
- HtmltoPng(HTML转PNG格式)
- SvgToPng(SVG转PNG格式)
- image-translate(图片翻译)
- image-translate-query(图片翻译结果)
- image-translate-redo(图片翻译修改)
- Flux-selfie(自拍照片风格化)
- Trellis(图片转3D模型)
- Pose-Transfer(人物姿态变换)
- Pose-Transfer(人物姿态变换结果)
- Virtual-Tryon(虚拟 穿衣)
- Virtual-Tryon(虚拟穿衣结果)
- Denoise(AI降噪)
- Deblur(AI去模糊)
- SAM(AI生成MASK图)
- Vectorizer
- Stability.ai
- Fast Upscale(快速图片放大)
- Creative Upscale(创意图片放大)
- Conservative Upscale(保守图片放大)
- Fetch Creative Upscale(超级图片放大)
- Erase(物体消除)
- Inpaint(图片修改)
- Outpaint(图片扩展)
- Search-and-replace(内容替换)
- Search-and-recolor(内容重着色)
- Remove-background(背景消除)
- Sketch(草图转图片)
- Structure(以图生图)
- Style(风格一致性)
- Replace-Background(更换背景)
- Stable-Fast-3D(图片转3D模型)
- Stable-Point-3D(图片转3D模型新版)
- Glif
- Clipdrop
- Recraft
- BRIA
- Remove Background(背景消除)
- Blur Background(背景模糊)
- Generate Background(背景生成)
- Erase Foreground(擦除前景)
- Eraser(物体擦除)
- Expand Image(图片扩展)
- Increase Resolution(图片放大)
- Crop(图片裁切)
- Cutout(产品图裁剪)
- Packshot(产品图特写)
- Shadow (产品图阴影)
- Scene (产品图场景生成)
- Caption(图片描述)
- Register(图片上传)
- Mask(图片分割)
- Presenter info (人脸分析)
- Modify Presenter(人脸修改)
- Delayer Image(图片转PSD)
- Flux
- Hyper3D
- Tripo3D
- FASHN
- Ideogram
- Doubao即梦
- Kling可灵
- 阶跃星辰
- Bagel
- 视频生成
- 统一接口
- 302.AI
- Stable Diffusion
- Luma AI
- Runway
- Kling可灵
- 302格式
- Txt2Video(文生视频1.0-快速-5秒)
- Txt2Video_HQ(文生视频1.5-高清-5秒)
- Txt2Video_HQ(文生视频1.5-高清-10秒)
- Image2Video(图生视频1.0-快速-5秒)
- Image2Video(图生视频1.0-快速-10秒)
- Image2Video(图生视频1.5-快速-5秒)
- Image2Video(图生视频1.5-快速-10秒)
- Image2Video_HQ(图生视频1.5-高清-5秒)
- Image2Video_HQ(图生视频1.5-高清-10秒)
- Txt2Video(文生视频1.6-标准-5秒)
- Txt2Video(文生视频1.6-标准-10秒)
- Txt2Video(文生视频1.6-高清-5秒)
- Image2Video(图生视频1.6-标准-5秒)
- Txt2Video(文生视频1.6-高清-10秒)
- Image2Video(图生视频1.6-标准-10秒)
- Image2Video(图生视频1.6-高清-5秒)
- Image2Video(图生视频1.6-高清-10秒)
- Txt2Video(文生视频2.0-高清-5秒)
- Image2Video(图生视频2.0-高清-5秒)
- Image2Video(图生视频2.0-高清-10秒)
- Image2Video(图生视频2.1-5秒)
- Image2Video(图生视频2.1-10秒)
- Image2Video(图生视频2.1-高清-5秒)
- Image2Video(图生视频2.1-高清-10秒)
- Txt2Video(文生视频2.1-大师版-5秒)
- Txt2Video(文生视频2.1-大师版-10秒)
- Image2Video(图生视频2.1-大师版-5秒)
- Image2Video(图生视频2.1-大师版-10秒)
- Image2Video(多图参考)
- Extend_Video(视频扩展)
- Fetch(获取任务结果)
- 官方格式
- 302格式
- CogVideoX智谱
- Minimax海螺
- Pika
- PixVerse
- Genmo
- Hedra
- Haiper
- Sync.
- Lightricks
- Hunyuan混元
- Vidu
- 通义万相
- 即梦
- 硅基流动
- 昆仑万维
- Higgsfield
- 蝉镜数字人
- Midjourney
- 音视频处理
- 统一接口
- 302.AI
- OpenAI
- Azure
- Suno
- 豆包
- Fish Audio
- Minimax
- Dubbingx
- Udio
- Elevenlabs
- Speech-to-text(语音转文字)POST
- Speech-to-text(异步获取结果)GET
- TTS-Multilingual-v2(文字转语音同步)POST
- TTS-Multilingual-v2(文字转语音异步)POST
- TTS-Multilingual-v2(异步获取结果)GET
- TTS-Flash-v2.5(文字转语音同步)POST
- TTS-Flash-v2.5(文字转语音异步)POST
- TTS-Flash-v2.5(异步获取结果)GET
- Text-to-speech(文字转语音)POST
- Text-to-speech(获取model_id)GET
- Text-to-speech(获取voice_id)GET
- Mureka
- 硅基流动
- Google
- 蝉镜数字人
- 信息处理
- 统一搜索接口
- 302.AI
- 管理后台
- 信息搜索
- Xiaohongshu_Search(小红书搜索笔记)
- Xiaohongshu_Note(小红书获取笔记)
- Xiaohongshu_Note(小红书获取笔记V2)
- Xiaohongshu_Comments(小红书获取笔记评论)
- Tiktok_Search(Tiktok搜索视频)
- Douyin_Search(抖音搜索视频)
- Twitter_Search(X搜索内容)
- Twitter_Post(X获取用户帖子)
- Twitter_User(X获取用户信息)
- Weibo_Post(微博获取用户 帖子)
- Search_Video(Youtube搜索视频)
- Youtube_Info(Youtube获取视频信息)
- Youtube_Subtitles(Youtube获取字幕)
- Bilibili_Info(B站获取视频信息)
- MP_Article_List(获取微信公众号文章列表)
- MP_Article(获取微信公众号文章)
- Zhihu_AI_Search(知乎AI搜索)
- Zhihu_AI_Search(获取知乎AI搜索结果)
- Zhihu_Hot_List(知乎热榜)
- Video_Data(获取视频数据)
- 文件处理
- 代码运行
- 远程浏览器
- Paper2Code
- Tavily
- SearchAPI
- Search1API
- Exa
- 博查AI
- Doc2x
- Glif
- Jina
- DeepL
- RSSHub
- 流光卡片
- 有道
- Mistral
- Firecrawl
- RAG相关
- 工具API
- 帮助中心
Text-to-speech(获取model_id)
开发中
正式环境
https://api.302.ai
正式环境
https://api.302.ai
GET
https://api.302.ai
参数can_do_text_to_speech 为 true的可用
请求参数
Header 参数
Authorization
string
可选
示例值:
Bearer {{YOUR_API_KEY}}
示例代码
Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
请求示例请求示例
Shell
JavaScript
Java
Swift
curl --location --request GET 'https://api.302.ai/elevenlabs/models' \
--header 'Authorization: Bearer '
返回响应
🟢200成功
application/json
Body
array of:
model_id
string
必需
name
string
必需
can_be_finetuned
boolean
必需
can_do_text_to_speech
boolean
必需
can_do_voice_conversion
boolean
必需
can_use_style
boolean
必需
can_use_speaker_boost
boolean
必需
serves_pro_voices
boolean
必需
token_cost_factor
integer
必需
description
string
必需
requires_alpha_access
boolean
必需
max_characters_request_free_user
integer
必需
max_characters_request_subscribed_user
integer
必需
maximum_text_length_per_request
integer
必需
languages
array [object {2}]
必需
language_id
string
必需
name
string
必需
model_rates
object
必需
character_cost_multiplier
integer | number
必需
concurrency_group
string
必需
示例
[
{
"model_id": "eleven_multilingual_v2",
"name": "Eleven Multilingual v2",
"can_be_finetuned": true,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": true,
"can_use_speaker_boost": true,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our most life-like, emotionally rich mode in 29 languages. Best for voice overs, audiobooks, post-production, or any other content creation needs.",
"requires_alpha_access": false,
"max_characters_request_free_user": 10000,
"max_characters_request_subscribed_user": 10000,
"maximum_text_length_per_request": 10000,
"languages": [
{
"language_id": "en",
"name": "English"
},
{
"language_id": "ja",
"name": "Japanese"
},
{
"language_id": "zh",
"name": "Chinese"
},
{
"language_id": "de",
"name": "German"
},
{
"language_id": "hi",
"name": "Hindi"
},
{
"language_id": "fr",
"name": "French"
},
{
"language_id": "ko",
"name": "Korean"
},
{
"language_id": "pt",
"name": "Portuguese"
},
{
"language_id": "it",
"name": "Italian"
},
{
"language_id": "es",
"name": "Spanish"
},
{
"language_id": "id",
"name": "Indonesian"
},
{
"language_id": "nl",
"name": "Dutch"
},
{
"language_id": "tr",
"name": "Turkish"
},
{
"language_id": "fil",
"name": "Filipino"
},
{
"language_id": "pl",
"name": "Polish"
},
{
"language_id": "sv",
"name": "Swedish"
},
{
"language_id": "bg",
"name": "Bulgarian"
},
{
"language_id": "ro",
"name": "Romanian"
},
{
"language_id": "ar",
"name": "Arabic"
},
{
"language_id": "cs",
"name": "Czech"
},
{
"language_id": "el",
"name": "Greek"
},
{
"language_id": "fi",
"name": "Finnish"
},
{
"language_id": "hr",
"name": "Croatian"
},
{
"language_id": "ms",
"name": "Malay"
},
{
"language_id": "sk",
"name": "Slovak"
},
{
"language_id": "da",
"name": "Danish"
},
{
"language_id": "ta",
"name": "Tamil"
},
{
"language_id": "uk",
"name": "Ukrainian"
},
{
"language_id": "ru",
"name": "Russian"
}
],
"model_rates": {
"character_cost_multiplier": 1.0
},
"concurrency_group": "standard"
},
{
"model_id": "eleven_flash_v2_5",
"name": "Eleven Flash v2.5",
"can_be_finetuned": true,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our ultra low latency model in 32 languages. Ideal for conversational use cases.",
"requires_alpha_access": false,
"max_characters_request_free_user": 40000,
"max_characters_request_subscribed_user": 40000,
"maximum_text_length_per_request": 40000,
"languages": [
{
"language_id": "en",
"name": "English"
},
{
"language_id": "ja",
"name": "Japanese"
},
{
"language_id": "zh",
"name": "Chinese"
},
{
"language_id": "de",
"name": "German"
},
{
"language_id": "hi",
"name": "Hindi"
},
{
"language_id": "fr",
"name": "French"
},
{
"language_id": "ko",
"name": "Korean"
},
{
"language_id": "pt",
"name": "Portuguese"
},
{
"language_id": "it",
"name": "Italian"
},
{
"language_id": "es",
"name": "Spanish"
},
{
"language_id": "ru",
"name": "Russian"
},
{
"language_id": "id",
"name": "Indonesian"
},
{
"language_id": "nl",
"name": "Dutch"
},
{
"language_id": "tr",
"name": "Turkish"
},
{
"language_id": "fil",
"name": "Filipino"
},
{
"language_id": "pl",
"name": "Polish"
},
{
"language_id": "sv",
"name": "Swedish"
},
{
"language_id": "bg",
"name": "Bulgarian"
},
{
"language_id": "ro",
"name": "Romanian"
},
{
"language_id": "ar",
"name": "Arabic"
},
{
"language_id": "cs",
"name": "Czech"
},
{
"language_id": "el",
"name": "Greek"
},
{
"language_id": "fi",
"name": "Finnish"
},
{
"language_id": "hr",
"name": "Croatian"
},
{
"language_id": "ms",
"name": "Malay"
},
{
"language_id": "sk",
"name": "Slovak"
},
{
"language_id": "da",
"name": "Danish"
},
{
"language_id": "ta",
"name": "Tamil"
},
{
"language_id": "uk",
"name": "Ukrainian"
},
{
"language_id": "hu",
"name": "Hungarian"
},
{
"language_id": "no",
"name": "Norwegian"
},
{
"language_id": "vi",
"name": "Vietnamese"
}
],
"model_rates": {
"character_cost_multiplier": 0.5
},
"concurrency_group": "turbo"
},
{
"model_id": "eleven_turbo_v2_5",
"name": "Eleven Turbo v2.5",
"can_be_finetuned": true,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our high quality, low latency model in 32 languages. Best for developer use cases where speed matters and you need non-English languages.",
"requires_alpha_access": false,
"max_characters_request_free_user": 40000,
"max_characters_request_subscribed_user": 40000,
"maximum_text_length_per_request": 40000,
"languages": [
{
"language_id": "en",
"name": "English"
},
{
"language_id": "ja",
"name": "Japanese"
},
{
"language_id": "zh",
"name": "Chinese"
},
{
"language_id": "de",
"name": "German"
},
{
"language_id": "hi",
"name": "Hindi"
},
{
"language_id": "fr",
"name": "French"
},
{
"language_id": "ko",
"name": "Korean"
},
{
"language_id": "pt",
"name": "Portuguese"
},
{
"language_id": "it",
"name": "Italian"
},
{
"language_id": "es",
"name": "Spanish"
},
{
"language_id": "ru",
"name": "Russian"
},
{
"language_id": "id",
"name": "Indonesian"
},
{
"language_id": "nl",
"name": "Dutch"
},
{
"language_id": "tr",
"name": "Turkish"
},
{
"language_id": "fil",
"name": "Filipino"
},
{
"language_id": "pl",
"name": "Polish"
},
{
"language_id": "sv",
"name": "Swedish"
},
{
"language_id": "bg",
"name": "Bulgarian"
},
{
"language_id": "ro",
"name": "Romanian"
},
{
"language_id": "ar",
"name": "Arabic"
},
{
"language_id": "cs",
"name": "Czech"
},
{
"language_id": "el",
"name": "Greek"
},
{
"language_id": "fi",
"name": "Finnish"
},
{
"language_id": "hr",
"name": "Croatian"
},
{
"language_id": "ms",
"name": "Malay"
},
{
"language_id": "sk",
"name": "Slovak"
},
{
"language_id": "da",
"name": "Danish"
},
{
"language_id": "ta",
"name": "Tamil"
},
{
"language_id": "uk",
"name": "Ukrainian"
},
{
"language_id": "vi",
"name": "Vietnamese"
},
{
"language_id": "no",
"name": "Norwegian"
},
{
"language_id": "hu",
"name": "Hungarian"
}
],
"model_rates": {
"character_cost_multiplier": 0.5
},
"concurrency_group": "turbo"
},
{
"model_id": "eleven_turbo_v2",
"name": "Eleven Turbo v2",
"can_be_finetuned": true,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our English-only, low latency model. Best for developer use cases where speed matters and you only need English. Performance is on par with Turbo v2.5.",
"requires_alpha_access": false,
"max_characters_request_free_user": 30000,
"max_characters_request_subscribed_user": 30000,
"maximum_text_length_per_request": 30000,
"languages": [
{
"language_id": "en",
"name": "English"
}
],
"model_rates": {
"character_cost_multiplier": 0.5
},
"concurrency_group": "turbo"
},
{
"model_id": "eleven_flash_v2",
"name": "Eleven Flash v2",
"can_be_finetuned": true,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our ultra low latency model in english. Ideal for conversational use cases.",
"requires_alpha_access": false,
"max_characters_request_free_user": 30000,
"max_characters_request_subscribed_user": 30000,
"maximum_text_length_per_request": 30000,
"languages": [
{
"language_id": "en",
"name": "English"
}
],
"model_rates": {
"character_cost_multiplier": 0.5
},
"concurrency_group": "turbo"
},
{
"model_id": "eleven_multilingual_v1",
"name": "Eleven Multilingual v1",
"can_be_finetuned": false,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our first Multilingual model, capability of generating speech in 10 languages. Now outclassed by Multilingual v2 (for content creation) and Turbo v2.5 (for low latency use cases).",
"requires_alpha_access": false,
"max_characters_request_free_user": 10000,
"max_characters_request_subscribed_user": 10000,
"maximum_text_length_per_request": 10000,
"languages": [
{
"language_id": "en",
"name": "English"
},
{
"language_id": "de",
"name": "German"
},
{
"language_id": "pl",
"name": "Polish"
},
{
"language_id": "es",
"name": "Spanish"
},
{
"language_id": "it",
"name": "Italian"
},
{
"language_id": "fr",
"name": "French"
},
{
"language_id": "pt",
"name": "Portuguese"
},
{
"language_id": "hi",
"name": "Hindi"
},
{
"language_id": "ar",
"name": "Arabic"
}
],
"model_rates": {
"character_cost_multiplier": 1.0
},
"concurrency_group": "standard"
},
{
"model_id": "eleven_multilingual_sts_v2",
"name": "Eleven Multilingual v2",
"can_be_finetuned": true,
"can_do_text_to_speech": false,
"can_do_voice_conversion": true,
"can_use_style": true,
"can_use_speaker_boost": true,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our cutting-edge, multilingual speech-to-speech model is designed for situations that demand unparalleled control over both the content and the prosody of the generated speech across various languages.",
"requires_alpha_access": false,
"max_characters_request_free_user": 10000,
"max_characters_request_subscribed_user": 10000,
"maximum_text_length_per_request": 10000,
"languages": [
{
"language_id": "en",
"name": "English"
},
{
"language_id": "ja",
"name": "Japanese"
},
{
"language_id": "zh",
"name": "Chinese"
},
{
"language_id": "de",
"name": "German"
},
{
"language_id": "hi",
"name": "Hindi"
},
{
"language_id": "fr",
"name": "French"
},
{
"language_id": "ko",
"name": "Korean"
},
{
"language_id": "pt",
"name": "Portuguese"
},
{
"language_id": "it",
"name": "Italian"
},
{
"language_id": "es",
"name": "Spanish"
},
{
"language_id": "ru",
"name": "Russian"
},
{
"language_id": "id",
"name": "Indonesian"
},
{
"language_id": "nl",
"name": "Dutch"
},
{
"language_id": "tr",
"name": "Turkish"
},
{
"language_id": "fil",
"name": "Filipino"
},
{
"language_id": "pl",
"name": "Polish"
},
{
"language_id": "sv",
"name": "Swedish"
},
{
"language_id": "bg",
"name": "Bulgarian"
},
{
"language_id": "ro",
"name": "Romanian"
},
{
"language_id": "ar",
"name": "Arabic"
},
{
"language_id": "cs",
"name": "Czech"
},
{
"language_id": "el",
"name": "Greek"
},
{
"language_id": "fi",
"name": "Finnish"
},
{
"language_id": "hr",
"name": "Croatian"
},
{
"language_id": "ms",
"name": "Malay"
},
{
"language_id": "sk",
"name": "Slovak"
},
{
"language_id": "da",
"name": "Danish"
},
{
"language_id": "ta",
"name": "Tamil"
},
{
"language_id": "uk",
"name": "Ukrainian"
}
],
"model_rates": {
"character_cost_multiplier": 1.0
},
"concurrency_group": "standard"
},
{
"model_id": "eleven_monolingual_v1",
"name": "Eleven English v1",
"can_be_finetuned": false,
"can_do_text_to_speech": true,
"can_do_voice_conversion": false,
"can_use_style": false,
"can_use_speaker_boost": false,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our first ever text to speech model. Now outclassed by Multilingual v2 (for content creation) and Turbo v2.5 (for low latency use cases).",
"requires_alpha_access": false,
"max_characters_request_free_user": 10000,
"max_characters_request_subscribed_user": 10000,
"maximum_text_length_per_request": 10000,
"languages": [
{
"language_id": "en",
"name": "English"
}
],
"model_rates": {
"character_cost_multiplier": 1.0
},
"concurrency_group": "standard"
},
{
"model_id": "eleven_english_sts_v2",
"name": "Eleven English v2",
"can_be_finetuned": false,
"can_do_text_to_speech": false,
"can_do_voice_conversion": true,
"can_use_style": true,
"can_use_speaker_boost": true,
"serves_pro_voices": false,
"token_cost_factor": 1.0,
"description": "Our state-of-the-art speech to speech model suitable for scenarios where you need maximum control over the content and prosody of your generations.",
"requires_alpha_access": false,
"max_characters_request_free_user": 5000,
"max_characters_request_subscribed_user": 5000,
"maximum_text_length_per_request": 5000,
"languages": [
{
"language_id": "en",
"name": "English"
}
],
"model_rates": {
"character_cost_multiplier": 1.0
},
"concurrency_group": "standard"
}
]
修改于 2025-07-01 06:35:12