kobold_transcribe
Convert audio to text using Whisper. Specify language or use default settings for transcription. Requires audio input for processing.
Instructions
Transcribe audio using Whisper
Input Schema
Name | Required | Description | Default |
---|---|---|---|
apiUrl | No | http://localhost:5001 | |
audio | Yes | ||
language | No |
Input Schema (JSON Schema)
You must be authenticated.
Other Tools from Kobold MCP Server
- kobold_abort
- kobold_chat
- kobold_complete
- kobold_detokenize
- kobold_generate
- kobold_img2img
- kobold_interrogate
- kobold_last_logprobs
- kobold_max_context_length
- kobold_max_length
- kobold_model_info
- kobold_perf_info
- kobold_sd_models
- kobold_sd_samplers
- kobold_token_count
- kobold_transcribe
- kobold_tts
- kobold_txt2img
- kobold_version
- kobold_web_search
Related Tools
- @Ichigo3766/audio-transcriber-mcp
- @mamertofabian/elevenlabs-mcp-server
- @vmehta14/whissle-mcp
- @PsychArch/minimax-mcp-tools
- @pinkpixel-dev/MCPollinations