plug.directory
Add my server

Voxtral

by tobdeberco.huggingface.tobdeber/voxtral

  • Remote endpoint
  • 7 tools
  • Voxtral__update_cpu_eta 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
  • Voxtral__update_cpu_eta_1 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
  • Voxtral__update_cpu_eta_2 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
  • Voxtral__update_cpu_eta_3 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
  • Voxtral__update_cpu_eta_4 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
  • Voxtral_process_audio Process audio with selected Voxtral model and return the generated response. This function takes an audio file and processes it using the selected Voxtral model to generate a transcription in the specified language. 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: String containing the transcribed text from the audio file, or an error message, if the audio file is missing or an invalid model is selected.
  • Voxtral_process_audio_cpu Process audio on CPU (up to 16 threads) instead of ZeroGPU. Uses its own CPU-resident copies of the models (loaded lazily and cached), so it never consumes GPU quota. Much slower than the GPU path, but free. 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

As the server's own listing gives them. We never call a tool.