Skip to content

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

Add EvoLink LLM provider

EvolinkAI84a136a939bb
diff --git a/README-en.md b/README-en.md
index d5335f15..d083e24a 100644
--- a/README-en.md
+++ b/README-en.md
@@ -95,7 +95,7 @@ materials, video subtitles, and video background music before synthesizing a hig
- [x] Supports **background music**, either random or specified music files, with adjustable `background music volume`
- [x] Video material sources are **high-definition** and **royalty-free**, and you can also use your own **local materials**
- [x] Supports multiple stock video providers: **Pexels**, **Pixabay**, and **Coverr**
-- [x] Supports integration with various models such as **OpenAI**, **AIHubMix**, **AIML API**, **Moonshot**, **Azure**, **gpt4free**, **one-api**, **Qwen**, **Google Gemini**, **Ollama**, **DeepSeek**, **MiniMax**, **ERNIE**, **Pollinations**, **ModelScope** and more
+- [x] Supports integration with various models such as **OpenAI**, **AIHubMix**, **AIML API**, **EvoLink**, **Moonshot**, **Azure**, **gpt4free**, **one-api**, **Qwen**, **Google Gemini**, **Ollama**, **DeepSeek**, **MiniMax**, **ERNIE**, **Pollinations**, **ModelScope** and more
## Video Demos 📺
diff --git a/README.md b/README.md
index d3fb6e3c..27d9935a 100644
--- a/README.md
+++ b/README.md
@@ -92,7 +92,7 @@
- [x] 支持 **背景音乐**,随机或者指定音乐文件,可设置`背景音乐音量`
- [x] 视频素材来源 **高清**,而且 **无版权**,也可以使用自己的 **本地素材**
- [x] 支持多种素材源:**Pexels**、**Pixabay**、**Coverr**
-- [x] 支持 **OpenAI**、**AIHubMix**、**AIML API**、**Moonshot**、**Azure**、**gpt4free**、**one-api**、**通义千问**、**Google Gemini**、**Ollama**、**DeepSeek**、**MiniMax**、 **文心一言**, **Pollinations**、**ModelScope** 等多种模型接入
+- [x] 支持 **OpenAI**、**AIHubMix**、**AIML API**、**EvoLink**、**Moonshot**、**Azure**、**gpt4free**、**one-api**、**通义千问**、**Google Gemini**、**Ollama**、**DeepSeek**、**MiniMax**、 **文心一言**, **Pollinations**、**ModelScope** 等多种模型接入
- [x] 支持一键 **跨平台发布**,生成完成后自动上传至 **TikTok**、**Instagram** 和 **YouTube Shorts**(需 [Upload-Post](https://upload-post.com) 账号;YouTube 发布时自动标注 AI 生成内容);在 `config.toml` 中配置 `upload_post_platforms`、`upload_post_youtube_privacy_status` 等参数
## 视频演示 📺
diff --git a/app/services/llm.py b/app/services/llm.py
index 22533252..642b361f 100644
--- a/app/services/llm.py
+++ b/app/services/llm.py
@@ -260,6 +260,14 @@ def _generate_response(prompt: str) -> str:
base_url = config.app.get("minimax_base_url", "")
if not base_url:
base_url = "https://api.minimax.io/v1"
+ elif llm_provider == "evolink":
+ api_key = config.app.get("evolink_api_key")
+ model_name = config.app.get("evolink_model_name")
+ base_url = config.app.get("evolink_base_url", "")
+ if not base_url:
+ base_url = "https://direct.evolink.ai/v1"
+ if not model_name:
+ model_name = "gpt-5.5"
elif llm_provider == "mimo":
api_key = config.app.get("mimo_api_key")
model_name = config.app.get("mimo_model_name")
diff --git a/config.example.toml b/config.example.toml
index fac44cc3..55831a60 100644
--- a/config.example.toml
+++ b/config.example.toml
@@ -62,6 +62,7 @@ coverr_api_keys = []
# oneapi
# cloudflare
# minimax
+# evolink (OpenAI-compatible multi-model AI gateway)
# mimo (Xiaomi MiMo)
# ernie (文心一言)
# modelscope (魔搭社区)
@@ -179,6 +180,15 @@ minimax_api_key = ""
minimax_base_url = "https://api.minimax.io/v1"
minimax_model_name = "MiniMax-M3"
+########## EvoLink API Key
+# EvoLink is an OpenAI-compatible gateway for language models.
+# Visit https://evolink.ai/dashboard/keys to get your API key.
+# API documentation: https://docs.evolink.ai/en/api-manual/language-series
+# Available models include gpt-5.5, gpt-5.4, gpt-5.2, deepseek-v4-flash, deepseek-v4-pro, gemini-3.1-pro, and doubao-seed-2.0-pro.
+evolink_api_key = ""
+evolink_base_url = "https://direct.evolink.ai/v1"
+evolink_model_name = "gpt-5.5"
+
########## Xiaomi MiMo API Key
# Xiaomi MiMo API is OpenAI-compatible.
# Visit https://platform.xiaomimimo.com/docs/zh-CN/quick-start/first-api-call to get more details.
diff --git a/test/services/test_llm.py b/test/services/test_llm.py
index 79778fdb..576545b9 100644
--- a/test/services/test_llm.py
+++ b/test/services/test_llm.py
@@ -449,6 +449,48 @@ class TestLiteLLMProvider(unittest.TestCase):
)
self.assertEqual(result, "helloaimlapi")
+ def test_evolink_provider_uses_openai_compatible_client(self):
+ """
+ EvoLink exposes OpenAI-compatible Chat Completions at direct.evolink.ai.
+ The provider should keep its own default endpoint and model instead of
+ requiring users to overload the generic OpenAI settings.
+ """
+ config.app["llm_provider"] = "evolink"
+ config.app["evolink_api_key"] = "evolink-key"
+ config.app["evolink_base_url"] = ""
+ config.app["evolink_model_name"] = ""
+
+ class FakeCompletions:
+ def create(self, **kwargs):
+ self.kwargs = kwargs
+ message = types.SimpleNamespace(content="hello\nevolink")
+ choice = types.SimpleNamespace(message=message)
+ return types.SimpleNamespace(choices=[choice])
+
+ fake_completions = FakeCompletions()
+ fake_client = types.SimpleNamespace(
+ chat=types.SimpleNamespace(completions=fake_completions)
+ )
+
+ with (
+ patch.object(llm, "OpenAI", return_value=fake_client) as openai_client,
+ patch.object(llm, "ChatCompletion", types.SimpleNamespace),
+ ):
+ result = llm._generate_response("Say hello")
+
+ openai_client.assert_called_once_with(
+ api_key="evolink-key",
+ base_url="https://direct.evolink.ai/v1",
+ )
+ self.assertEqual(
+ fake_completions.kwargs,
+ {
+ "model": "gpt-5.5",
+ "messages": [{"role": "user", "content": "Say hello"}],
+ },
+ )
+ self.assertEqual(result, "helloevolink")
+
def test_grok_provider_still_uses_existing_path(self):
config.app["llm_provider"] = "grok"
config.app["grok_api_key"] = ""