Set up Bob (macOS translator)
Selection and screenshot translator for macOS; add the OpenAI Translator plugin to use CherryChat
- API format: OpenAI Chat Completions
- Base URL format: Full path to /v1/chat/completions (https://gpt.cherrychat.org/v1/chat/completions)
- Recommended model: deepseek-v4-flash, gpt-5.4-mini
- Platforms: macOS
Steps
Install the OpenAI Translator plugin
Make sure Bob is 1.8.0 or later. Download the latest openai-translator.bobplugin from the plugin's GitHub Releases page and double-click it; Bob confirms the install.
Add the translation service
Open Bob Preferences → Services, select Text Translation, click "+" below the list and choose "OpenAI Translator".
Fill in the API key, model and API URL
Set Model to the custom option and type the model name; API URL must be the full address.
- API Key: sk-your-key
- Custom model: deepseek-v4-flash
- API URL: https://gpt.cherrychat.org/v1/chat/completions (Must end with /chat/completions)
Save and test
Leave Reasoning at Default and streaming on, then Save. Select some English text and press Bob's translate shortcut; a translation means it works.
Common pitfalls
- API URL must be the full https://gpt.cherrychat.org/v1/chat/completions ending in /chat/completions; /responses switches to the Responses API, and a bare domain is rejected.
- Do not leave API URL empty; the plugin would call OpenAI directly and reject the CherryChat key.
- Setting Reasoning to Off makes some models return parameter errors; Default is safest.
- Selection translation is light but frequent, so a cheap fast model such as deepseek-v4-flash is enough. Separate multiple keys with English commas.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| "API URL format is incorrect" | The URL does not end with /chat/completions | Change it to https://gpt.cherrychat.org/v1/chat/completions |
| Translation fails with 401 | The key is wrong or has spaces, or API URL is empty so requests go elsewhere | Copy the key again and make sure API URL is https://gpt.cherrychat.org/v1/chat/completions |
| Model not found | The custom model option is not selected, or the name is wrong | Choose the custom model option and enter deepseek-v4-flash |
| HTTP 402 or "insufficient balance" (billing_error in Claude format) | Your credits cannot cover this call. API calls are paid from credits only; memberships and unlimited plans do not apply | Top up any amount in the CherryChat Store, then retry after a few seconds |
| HTTP 429 Too Many Requests | Too many requests: by default 120 per minute per key and 8 at a time per account | Lower the concurrency or requests per second in the tool and wait for the Retry-After seconds; most tools retry on their own |
Guide checked 2026-11-02. The tool's screens may change; the official docs win if they differ.
Operated by UK Company CHERRYCHAT LTD · Company Number 16096119 · Support WeChat: JsnonoChat · Content is AI-generated — please verify before relying on it
