Local InferenceOpen SourceFreeActiveLocal hardware· intermediate · ~25 min setup
Local Voice-to-Text that Replaces WisprFlow
Run fully local dictation with whisper.cpp instead of paying for WisprFlow.
Run this workflow
See exactly what it produces before you build it.
Build this with your agent
One copy-paste hands Claude Code, Codex, or Cursor the full recipe, steps included, nothing to fetch.
Intended Use
Anyone dictating notes/code daily who currently pays for WisprFlow and wants to drop the subscription.
Not for
- Real-time captioning with sub-100ms latency
- Streaming long-form audio (>10 min), Whisper batches better
Replaces WisprFlow
The Stack
Tested Against
whisper.cpp@1.6Side effects & data flow
- Network
- none, local only
- Writes
- ./transcript.txt
- Credentials
- none required
Steps
- 1
Build whisper.cpp
Clone and compile the project, then download a quantized model.
git clone https://github.com/ggerganov/whisper.cpp && cd whisper.cpp && make - 2
Transcribe a sample
Run whisper on a short WAV and check the output.
./main -m models/ggml-base.en.bin -f samples/jfk.wav > transcript.txt
Eval, 1 fixture
Last passed: verified 1mo agosmoke-transcribecontainstimeout 120s · max $0Expected:
ask not
Results
Saves $12/month; works offline with no usage caps.
Did this work for you?
Our CI checks the setup runs. You tell us if the whole thing worked. Tell us straight.
Related workflows
- Prove your meeting-notes pipeline never phones home (and gates on consent)
- Unsloth: write parametric memory in with a fine-tune config
- Validate an Apple Core AI export entry and skill plugin before you touch a Mac
- Serve NVIDIA Nemotron 3 Ultra yourself for high-throughput agents (vLLM)
- Serve GLM-5.1 yourself for long-horizon agentic coding (vLLM)
- Serve MiniMax M3 yourself for agentic coding (vLLM)
Liked this workflow?
Get new verified workflows in WebAfterAI, three issues a week (Tue, Thu, Sat).