feat: add gemini-2.0 support!

Author: Huanshere

README.md

@@ -110,8 +110,8 @@ docker run -d -p 8501:8501 --gpus all videolingo
 
 ## API
 VideoLingo supports OpenAI-Like API format and various dubbing interfaces:
-- `claude-3-5-sonnet-20240620`, `gemini-1.5-pro-002`, `gpt-4o`, `deepseek-coder`, `Qwen2.5-72B-Instruct`, ... (sorted by performance)
-- `azure-tts`, `openai-tts`, `siliconflow-fishtts`, `fish-tts`, `GPT-SoVITS`, `edge-tts`, `custom-tts`(edit yourself in custom_tts.py)
+- `claude-3-5-sonnet-20240620`, **`gemini-2.0-flash-exp`**, `gpt-4o`, `deepseek-coder`, ... (sorted by performance)
+- `azure-tts`, `openai-tts`, `siliconflow-fishtts`, **`fish-tts`**, `GPT-SoVITS`, `edge-tts`, `*custom-tts`(ask gpt to help you define in custom_tts.py)
 
 > **Note:** VideoLingo is now integrated with [302.ai](https://gpt302.saaslink.net/C2oHR9), **one API KEY** for both LLM and TTS! Also supports fully local deployment using Ollama for LLM and Edge-TTS for dubbing, no cloud API required!
 

config.yaml

@@ -1,11 +1,11 @@
 # * Settings marked with * are advanced settings that won't appear in the Streamlit page and can only be modified manually in config.py
-version: "2.0.4"
+version: "2.1.2"
 ## ======================== Basic Settings ======================== ##
 # API settings
 api:
   key: 'YOUR_API_KEY'
   base_url: 'https://api.302.ai'
-  model: 'claude-3-5-sonnet-20240620'
+  model: 'gemini-2.0-flash-exp'
 
 # Language settings, written into the prompt, can be described in natural language
 target_language: '简体中文'
@@ -133,9 +133,7 @@ allowed_audio_formats:
 llm_support_json:
 - 'gpt-4o'
 - 'gpt-4o-mini'
-- 'gemini-1.5-flash-latest'
-- 'gemini-1.5-pro-latest'
-- 'gemini-1.5-pro-002'
+- 'gemini-2.0-flash-exp'
 - 'deepseek-coder'
 
 # have problems

docs/pages/docs/start.en-US.md

@@ -7,7 +7,8 @@ This project requires Large Language Models and TTS. For best quality, please us
 
 | Recommended Model | Recommended Provider | base_url | Price | Effect |
 |:-----|:---------|:---------|:-----|:---------|
-| claude-3-5-sonnet-20240620 | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $7.5 / 1M tokens | 🤩 |
+| gemini-2.0-flash-exp | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $0.3 / 1M tokens | 🥳 |
+| claude-3-5-sonnet-20240620 | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $15 / 1M tokens | 🤩 |
 | deepseek-coder | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | ¥2 / 1M tokens | 😃 |
 | qwen2.5-coder:32b | [Ollama](https://ollama.ai) | http://localhost:11434 | Local | 😃 |
 
@@ -20,7 +21,7 @@ VideoLingo provides multiple TTS integration methods. Here's a comparison (skip
 |:---------|:---------|:-----|:-----|:---------|:-----------|
 | 🔊 Azure TTS ⭐ | [302AI](https://gpt302.saaslink.net/C2oHR9) | Natural effect | Limited emotions | 🤩 | 😃 |
 | 🎙️ OpenAI TTS | [302AI](https://gpt302.saaslink.net/C2oHR9) | Realistic emotions | Chinese sounds foreign | 😕 | 🤩 |
-| 🎤 Fish TTS | [302AI](https://gpt302.saaslink.net/C2oHR9) | Authentic native | Limited official models | 😂 | 😂 |
+| 🎤 Fish TTS | [302AI](https://gpt302.saaslink.net/C2oHR9) | Authentic native | Limited official models | 🤩 | 😂 |
 | 🎙️ SiliconFlow FishTTS | [SiliconFlow](https://cloud.siliconflow.cn/i/ttKDEsxE) | Voice Clone | Unstable cloning effect | 😃 | 😃 |
 | 🗣 Edge TTS | Local | Completely free | Average effect | 😐 | 😐 |
 | 🗣️ GPT-SoVITS | Local | Best voice cloning | Only supports Chinese/English, requires local inference, complex setup | 🏆 | 🚫 |

docs/pages/docs/start.zh-CN.md

@@ -7,7 +7,8 @@
 
 | 推荐模型 | 推荐提供商 | base_url | 价格 | 效果 |
 |:-----|:---------|:---------|:-----|:---------|
-| claude-3-5-sonnet-20240620 | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $7.5 / 1M tokens | 🤩 |
+| gemini-2.0-flash-exp | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $0.3 / 1M tokens | 🥳 |
+| claude-3-5-sonnet-20240620 | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | $15 / 1M tokens | 🤩 |
 | deepseek-coder | [302AI](https://gpt302.saaslink.net/C2oHR9) | https://api.302.ai | ¥2 / 1M tokens | 😃 |
 | qwen2.5-coder:32b | [Ollama](https://ollama.ai) | http://localhost:11434 | 本地 | 😃 |
 

i18n/README.zh.md

@@ -112,8 +112,8 @@ docker run -d -p 8501:8501 --gpus all videolingo
 
 ## API
 本项目支持 OpenAI-Like 格式的 api 和多种配音接口：
-- `claude-3-5-sonnet-20240620`, `gemini-1.5-pro-002`, `gpt-4o`, `deepseek-coder`, `Qwen2.5-72B-Instruct`, ...（按效果排序）
-- `azure-tts`, `openai-tts`, `siliconflow-fishtts`, `fish-tts`, `GPT-SoVITS`, `edge-tts`, `custom-tts`(可在custom_tts.py中自行编辑)
+- `claude-3-5-sonnet-20240620`, **`gemini-2.0-flash-exp`**, `gpt-4o`, `deepseek-coder`, ...（按效果排序）
+- `azure-tts`, `openai-tts`, `siliconflow-fishtts`, **`fish-tts`**, `GPT-SoVITS`, `edge-tts`, `*custom-tts`(ask gpt to help you define in custom_tts.py)
 
 > **注意：** VideoLingo 现已与 [302.ai](https://gpt302.saaslink.net/C2oHR9) 集成，**一个 API KEY** 即可同时支持 LLM 和 TTS！同时也支持完全本地部署，使用 Ollama 作为 LLM 和 Edge-TTS 作为配音，无需云端 API！
 

i18n/中文/config.yaml

@@ -1,11 +1,11 @@
 # * 标有 * 的设置是高级设置，不会出现在 Streamlit 页面中，只能在 config.py 中手动修改
-version: "2.0.4"
+version: "2.1.2"
 ## ======================== 基本设置 ======================== ##
 # API 设置
 api:
   key: 'YOUR_API_KEY'
   base_url: 'https://api.302.ai'
-  model: 'claude-3-5-sonnet-20240620'
+  model: 'gemini-2.0-flash-exp'
 
 # 语言设置，写入提示词，可以用自然语言描述
 target_language: '简体中文'
@@ -133,10 +133,7 @@ allowed_audio_formats:
 llm_support_json:
 - 'gpt-4o'
 - 'gpt-4o-mini'
-- 'grok-beta'
-- 'gemini-1.5-flash-latest'
-- 'gemini-1.5-pro-latest'
-- 'gemini-1.5-pro-002'
+- 'gemini-2.0-flash-exp'
 - 'deepseek-coder'
 
 # 存在问题