Free
Added on Nov 09,2026
ScribeCrate is an open-source, self-hosted transcription API for private, local speech-to-text. It transcribes recordings, generates subtitles and translates speech into English on your own hardware.
It provides an OpenAI-compatible API powered by faster-whisper, with transcription and English translation through the /v1/audio/transcriptions and /v1/audio/translations endpoints. This means it can work with clients that already support the Whisper API.
Audio is processed on your own server. It can run offline when models are cached in advance and local-only mode is turned on.
Key features include optional speaker diarization through a local sherpa-onnx extension, output as JSON, text, verbose JSON, SRT or WebVTT, and streaming of decoded segments from uploaded files over SSE.
You can choose Whisper models from tiny through to large-v3 and large-v3-turbo. It accepts MP3, M4A, WAV, WebM, OGG, FLAC and other formats supported by FFmpeg.
It runs with Docker on amd64 or arm64 CPUs, or on NVIDIA GPUs using the CUDA image on amd64. Persistent caching keeps downloaded models across restarts. The default base model needs at least 700 MB of available RAM, and a Google Colab demo lets you try it without installing anything.
Pricing: ScribeCrate is open source and MIT licensed, so the software itself is free to use. You supply your own hardware or hosting.
It is suited to developers and teams transcribing meeting recordings, interviews and podcasts, creating subtitles, or building applications on the Whisper API while keeping audio private. It is part of the wider Self-Hosted AI Stack project.
By the PowerfulAI.tools Editorial Team · Updated 10 November 2026 · Researched with AI assistance and checked against the official ScribeCrate website · How we review tools
ScribeCrate is listed as free to use. Check ScribeCrate's website for any usage limits or paid upgrades.
Developers and privacy-conscious teams who want to transcribe meetings, interviews and podcasts on their own servers through a Whisper-style API.
Yes. It is open source under the MIT License, though you pay for your own hardware or cloud server, and models keep their own licences.
Yes, if models are cached in advance and WHISPER_LOCAL_ONLY is set to true. Optional aggregate usage counts can be turned off separately with WHISPER_DISABLE_USAGE_COUNTS=1.
No. The API mimics the OpenAI Whisper interface but runs locally with faster-whisper, so no OpenAI account is needed.
Popular alternatives to ScribeCrate include Easymeety.ai, Voice to Text and Otter.ai. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Easymeety.ai | Free | Sales reps, managers, researchers and students who record calls, standups, interviews or lectures on iPhone and want ins... |
| Voice to Text | Free | Students, writers and office workers who would rather dictate drafts than type them, in English or another supported lan... |
| Otter.ai | Freemium | Teams and professionals who want meetings transcribed and summarised with action items captured automatically. |
| RecCloud | Paid | Video creators and language learners who need transcripts, subtitles and translated voiceovers for web video. |
| Free Subtitles AI | Freemium | Video creators and editors who need time-stamped subtitles and translations for their footage without typing them out. |
Own ScribeCrate? Add this badge to your website.
Leave a review for the community
No Review Found
