Loading ToolBench

Reading the current corpus…

ffvoice-engine MCP server · F · ToolBench

ffvoice-engine

Offline speech recognition tools powered by ffvoice-engine. All audio processing happens locally on this device — nothing is transmitted to any external server.

2026-07-28+STDIO3 tools

0/100

Definition Quality0

Protocol Readiness0

SupportabilityNot measured-

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Tools (3)

capture_and_transcriberead onlysource verified

Capture live microphone audio for a given duration and transcribe it. Everything runs locally on this device — no audio is transmitted anywhere. VAD (Voice Activity Detection) segments the stream into speech chunks which are each transcribed individually by Whisper ASR.

list_audio_devicesread onlysource verified

List all audio input/output devices available on this machine. Uses PortAudio under the hood; no data leaves the device.

transcribe_fileread onlysource verified

Transcribe a local audio file to text using offline Whisper ASR. Processing is fully on-device — no audio is sent anywhere. Supports WAV, FLAC, and any format that whisper.cpp can read.

Score history

Overall score trend

First recorded score · v2 rubric

0/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	0	2026-07-28+	v2