Available for macOS and Windows

PipScribe

Bring every word back to the moment it was spoken.

A local AI transcription and subtitle workspace that turns long audio and video into searchable, editable, export-ready timed text.

Download for macOS macOS 12+ Download for Windows Windows 10/11

PipScribe word-level timeline and transcription workspace — Word-level timeline: replay segments, identify speakers, and shape subtitles without losing the source audio.

PipScribe AI summary and generation settings — AI summaries: create structured summaries from the transcript while preserving timestamps and speaker context.

PipScribe local model manager and Metal inference status — Local models and inference: choose Qwen3, Parakeet, or Whisper for each job, accelerated by Metal, CUDA, or Vulkan.

Word-level timeline Replay segments, identify speakers, and shape subtitles without losing the source audio.

Interview_July.mov Completed

00:12:06 → 00:12:10Maya Reed

The timing is what makes the transcript useful later.

00:12:10 → 00:12:15Daniel Hart

Everywordstaysconnectedtothemomentitwasspoken.

00:12:15 → 00:12:19Maya Reed

That makes review much faster than scrubbing through the whole recording.

Local transcriptionSpeaker recognitionWord-level timestampsTranslation and subtitlesAI summaries and chat

Turn speech into working material

Not just text.Keep working.

From interviews to video footage, PipScribe keeps audio, text, and time connected so every later edit has a source.

Interviews and podcasts

Separate speakers and replay the original audio by segment.

Video and subtitles

Adjust timing, control subtitle length, and export.

Courses and research

Search long recordings and extract summaries and key ideas.

Meetings and archives

Record both sides of the conversation, then extract decisions and action items.

Windows meeting recording

Record the meeting.Leave with the work.

Capture a selected app and your microphone as separate tracks. When the meeting ends, PipScribe transcribes locally and turns the conversation into an editable meeting workspace.

01Capture both sidesKeep application audio and microphone audio separate and safely saved.
02Transcribe with contextGenerate word timestamps and speaker-aware segments after recording.
03Turn talk into follow-throughEdit the overview, decisions, action items, key moments, and open questions.

Meeting workspaceDual track

Application audioSelected meeting app

MicrophoneYour voice

Meeting summaryEditable

Decisions3

Confirmed outcomes stay easy to review.

Action items4

Track owners, timing, and completion.

Key moments6

Return to the exact point in the recording.

Open questions2

Keep unresolved topics visible.

Bring almost anything

Start with a fileor a video URL.

Import local audio or video, or paste a supported video URL. PipScribe prepares the media and adds the transcription to your local queue.

Drop audio or video here

Supports common formats readable by FFmpeg

MP3WAVM4AMP4MOVMKVWEBMMore

Paste a supported video URL

Transcribe locally after retrieving the media

Precise timing

Hear the sentence.See the exact word.

Qwen3-ASR word-level timestamps keep playback, review, and subtitle editing on the same timeline.

Reviewtheexactwordwithoutlosingyourplace.

00:16:41.240

Possible long pause 00:16:42 → 00:16:47 gap 4.9s

00:16:42.000

After transcription

Know who spoke,shape the final subtitle.

Speaker labels, translations, and subtitle versions share one timeline. Continue the work in one place without moving content between tools.

VOICE MAP 2 speakers detected

00:12:0600:12:15

Maya Reed00:12:06

First, verify the word-level timeline. Then refine the subtitle boundaries.

Daniel Hart00:12:10

That way, every edit can be checked against the original audio.

Rename and manage speaker labels for each project

Local models and our inference engine

Choose the model.Use the right hardware.

Match Parakeet, Qwen3, or Whisper to the task, then let PipScribe's own engine select the right local compute backend for your device.

Built for speed

Move through long recordings quickly. On an M3 MacBook, a 119-second test recording completed in as little as 3.3 seconds.

About 36× realtime Measured on an M3 MacBook Ideal for long recordings

LOCAL INFERENCE CORE PipScribe Engine

Handles model loading, audio processing, and inference scheduling, with CPU fallback when no compatible GPU is available.

APPLE SILICONNow

Metal

Accelerated on the Mac GPU.

NVIDIAWindows

CUDA

A dedicated NVIDIA backend.

AMD · INTELFlexible

Vulkan

Accelerated on supported GPUs.

The macOS release uses Metal. The Windows release uses Vulkan on compatible GPUs, with CPU processing available as a fallback.

Understand, organize, and ask more

Keep workingwith the transcript.

Summarize, extract key ideas, identify open questions, or chat with the current transcript. Edit the built-in prompts or create your own.

Interview_July · Current transcriptOllama · Local

Turn this interview into an actionable summary.

AI response

Every conclusion can return to the original audio.

Use word-level timing to locate the exact moment first, then review long pauses and subtitle boundaries. Summaries, corrections, and later edits all keep the same audio reference.

00:12:06 · Maya Reed: “First, verify the word-level timeline. Then refine the subtitle boundaries.”

Cloud or local. You decide.Use your own account or API key, or connect a model running on your computer.

OpenAIAnthropicGeminiQwenOpenRouterDeepSeekZ.aiOllama LocalLM Studio Local

A clear privacy boundary

Your original media stays on your computer.

Local by default. Online services connect only when you choose them.

Media is not uploadedAudio and video are processed on your computer

Local work stays localQwen3, Parakeet, Whisper, Ollama, and LM Studio

Online only by choiceTranslation and cloud AI run only when you enable them

Why PipScribe

Transcription, subtitles, and AI—in one workspace.

Go beyond text with timeline review, subtitle preparation, and AI-assisted content work.

PipScribe A complete local workflow Transcribe → review → subtitle → AI

Local transcription tools Focused on local transcription Transcribe → basic editing

Cloud transcription services Focused on processing uploads Upload → service processing

Swipe horizontally to compare

Feature comparison between PipScribe, local transcription tools, and cloud transcription services
Capability	PipScribe	Local transcription tools	Cloud transcription services
Original media processing	Local by default	Usually local	Upload required
Transcription model choice	Qwen3-ASR, Parakeet, and Whisper	Usually one or two model families	Chosen by the service
Word-level timeline	Playback, editing, and gap diagnostics	Basic playback and editing	Varies by service
Subtitle workflow	Timeline adjustments, subtitle versions, translation, and export	Partial support	Primarily generation and export
AI options	Local models or your own API	Varies by product	Built into the service
Batch processing	Files, folders, URLs, and a task queue	Usually file batches	Upload queue
Pricing model	One-time purchase	One-time purchase or subscription	Usually subscription or usage based

StrengthPartial or product-dependentLimited

Features vary by product, version, and plan. This table compares typical product positioning.

Download PipScribe

Choose your version

PipScribe is available for Apple Silicon Macs and 64-bit Windows PCs.

macOS

Apple Silicon

Transcribe audio and video locally on your Mac, then work with timelines, subtitles, and AI tools.

macOS 12 Monterey or later
Apple Silicon (M1 or newer)
8 GB memory minimum; 16 GB recommended
At least 5 GB free; installing multiple models requires more space

Download for macOS

Windows

64-bit

Transcribe files and record meetings locally on Windows, with optional Vulkan GPU acceleration.

Windows 10 or Windows 11 (64-bit)
8 GB memory minimum; 16 GB recommended
At least 5 GB free; installing multiple models requires more space
Vulkan acceleration requires a compatible GPU and driver

Download for Windows

Simple pricing

One license.No subscription.

Try every feature on your own files before deciding to buy.

One-time license

Single-device editionOne-time payment · Perpetual use ^US$59

1Active device UnlimitedLocal files PerpetualUse

Your license includes

Qwen3-ASR, Parakeet, and Whisper
Original media and local transcripts stay on your computer
Word-level timelines, subtitles, and translation
Batch queues and supported video URL imports
AI summaries and chat with local models or your own API

Optional online translation and AI services use your own account or API key; provider charges may apply. Ollama and LM Studio run locally and require no cloud API.

Buy license

Download trial

7-day full-feature trial · No payment required

14-day refund window · View refund policy

Before you start

Frequently asked questions

Which audio and video formats are supported?

PipScribe supports common formats readable by FFmpeg, including MP3, WAV, M4A, MP4, MOV, MKV, and WebM. Available codecs may vary by platform.

Can I transcribe a video URL directly?

You can paste supported video URLs into the queue. Availability may change with the source website's rules; local file imports are unaffected.

Can I transcribe without an internet connection?

After downloading a model, local file transcription does not require uploading your media to the cloud.

Can AI summaries and translation run entirely locally?

Yes. Use Ollama or LM Studio installed on your computer, or choose an online service when needed.

Which Windows systems are supported?

PipScribe supports 64-bit Windows 10 and Windows 11. Compatible GPUs can use Vulkan acceleration; CPU processing remains available.