UniSS_translate – 1 MCP server offers this tool
What it usually takes
audio_path– in 1 of 1mode– in 1 of 1target_language– in 1 of 1text_decoding– in 1 of 1timing– in 1 of 1transcript_text– in 1 of 1translation_text– in 1 of 1use_vad– in 1 of 1whisper_mode– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
UniSS Speech Translation co.huggingface.boneyland/uniss Translate speech to speech with UniSS, keeping the speaker's voice. The published wrapper around `_translate_ui`: same work, no gr.State in or out, because an api_name'd handler that returns State breaks every MCP tool call (see `_transcribe_ui`). The [start-end] prefixes carry everything the State carried. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: Translated speech at 16 kHz, the translation (one line per chunk, span-prefixed),, and the source transcription. | audio_path,mode,target_language,text_decoding,timing,transcript_text,translation_text,use_vad,whisper_mode | Not stated |