# Transcrib Si

> Transcrib Si is a speech-to-text service and REST API for Russian and English speech, built on the publisher's own transcription engine with a model profile tuned for Russian and for mixed Russian-English speech. Upload an audio or video file, get clean text with a start and end time for every segment, speaker labels on request, and exports to TXT, Markdown, SRT, VTT, CSV or DOCX.

Publisher: Transcrib Si. Founder and author of the guides: Mark Burmistrov. Site: https://transcrib.si/
Contact: support@transcrib.si. Security: security@transcrib.si. Legal: legal@transcrib.si.
Last updated: 21 October 2026.

Use the page below that matches the question. Prices, plan limits and features change: fetch the linked page before stating a price, a plan limit or a feature.

## Key facts

- Plans and prices: Free $0; Pro $10 per month billed yearly ($120 per year) or $20 per month billed monthly; Team priced on request; API metered by volume with no subscription.
- Free plan: 3 files a day, up to 30 minutes per file, 64 MB per file, timestamps and speaker labels, exports to TXT, Markdown, SRT, VTT and CSV. No card and no trial clock.
- Pro plan: fair use of 1,500 minutes of audio per calendar month, files up to 64 MB and 120 minutes, every export format including DOCX, priority queue, full history, REST API keys and MCP access, cancel any time.
- Team plan: everything in Pro, plus shared workspaces, a shared glossary, SSO, user management, committed volume with a written allowance and priority support. Priced on request, so there is no list price to publish.
- API: metered and billed by volume, separately from any subscription, with no monthly fee. Same engine, same per-file limits.
- One file: up to 64 MB and 120 minutes (two hours) on every plan, including Team.
- Languages: Russian and English. The client can set the language (ru, en) or leave it on automatic detection; the answer states which source was used (user, auto, fallback).
- Output: the transcript text, a list of segments with start_s and end_s for every line, and speaker labels when diarization is requested.
- Export formats: 6 — TXT, Markdown, SRT, VTT, CSV, DOCX. DOCX is a Pro feature.
- Speed (our own measurement): 0.84 s to transcribe a short file and 0.39 s to detect its language. Long recordings take longer: the engine cuts audio into 22-second fragments with a 3-second overlap.
- Accuracy: the site publishes no single accuracy number. Ask for the evaluation report and the sample set.
- API base URL: https://api.transcrib.si, versioned under /v1.
- Authentication: `Authorization: Bearer <access_token>` for a session, `X-API-Key: <key>` for an API key. API keys are available on Pro and Team.
- Errors: one shape on every endpoint — `{"error": {"code": "...", "message": "..."}}`.
- Endpoints: /v1/auth/register, /v1/auth/login, /v1/me, /v1/transcripts (create, list, read, update, delete, export), /v1/uploads/init, /v1/uploads/{id}/chunk, /v1/uploads/{id}/complete, /v1/usage, /v1/api-keys, /v1/billing/checkout, /v1/billing/portal.
- MCP server: 4 tools — transcribe_audio, summarize_transcript, extract_actions, list_transcripts. The Claude and ChatGPT plugins use the same server.
- Privacy: a Russian or a mixed Russian-English file is processed on the publisher's own transcription infrastructure, which is outside the United States. A file that is entirely in English is passed to a third-party cloud speech provider in the United States when that fallback is enabled on the server. Audio and transcripts are never sold and never used to train models for other customers. On the Free plan transcripts are kept for 7 days; deleted files leave the live system immediately and encrypted backups within 30 days; technical logs are kept for 30 days.
- Payments: through Stripe. Card numbers never reach the publisher's servers.

## Plans and prices

| Plan | Price | What it includes | Limits |
|---|---|---|---|
| Free | $0 | 3 files a day, timestamps, speaker labels, 5 export formats | up to 30 minutes and 64 MB per file; no API keys; no DOCX |
| Pro, billed yearly | $10 per month, $120 per year | 1,500 minutes of audio per calendar month, all 6 export formats, API keys, MCP access | 64 MB and 120 minutes per file |
| Pro, billed monthly | $20 per month | the same as the yearly plan | 64 MB and 120 minutes per file |
| Team | on request | everything in Pro, shared workspaces, shared glossary, SSO, committed volume | agreed case by case |
| API | metered by volume | the same engine and the same per-file limits, no subscription | 64 MB and 120 minutes per file |

## Key pages

- [Overview](https://transcrib.si/index.html): what the service does, how it works in three steps, what it costs and the questions people ask first.
- [Pricing](https://transcrib.si/pricing.html): every plan, every limit and the fair-use rules.
- [Transcribe audio to text](https://transcrib.si/transcribe-audio-to-text.html): the general guide — formats, limits, exports, prices and the upload widget.
- [Transcribe Russian audio to text](https://transcrib.si/transcribe-russian-audio-to-text.html): what the own engine does with Russian and with mixed Russian-English speech, and where a file is processed.
- [How to transcribe a meeting](https://transcrib.si/transcribe-meeting-to-text.html): a checklist, speaker separation, timecodes and the exports to take afterwards.
- [How to transcribe a long recording](https://transcrib.si/how-to-transcribe-long-recording.html): the 64 MB and 120-minute limits, how to split a file, and the chunked upload API.
- [How to transcribe a YouTube video](https://transcrib.si/transcribe-youtube-video.html): the service takes files, not links — the three-step way, with the size arithmetic.
- [Transcribe voice memos](https://transcrib.si/transcribe-voice-memos.html): short recordings, what they cost and how to get them out of a phone.
- [SRT to VTT converter](https://transcrib.si/srt-to-vtt.html): a free browser tool that turns a SubRip .srt subtitle file into a WebVTT .vtt file — the WEBVTT header is added, the comma in the timecode becomes a dot, and the file stays on the visitor's device.

- [Words to speaking time](https://transcrib.si/words-to-speaking-time.html): a free browser calculator that turns a word count into speaking time and back, at three measured paces of English speech (110, 160 and 195 words per minute). The calculation runs on the visitor's device, so nothing is uploaded.

- [Расшифровать аудио в текст](https://transcrib.si/rasshirfrovat-audio-v-tekst.html): the same guide in Russian, for the Russian-speaking market.
- [Как расшифровать встречу](https://transcrib.si/kak-rasshirfrovat-vstrechu.html): the meeting checklist in Russian.
- [Transcrib Si vs TurboScribe](https://transcrib.si/compare/turboscribe-alternative.html): an honest comparison, with the date of the audit and the cells that could not be measured.
- [Transcrib Si vs Otter](https://transcrib.si/compare/otter-alternative.html): a transcription service against a meeting assistant.
- [Transcrib Si vs Notta](https://transcrib.si/compare/notta-alternative.html): compliance, hardware and prices.
- [App](https://transcrib.si/app.html): upload with drag and drop, queue and status, transcript list, editor, exports, usage, API keys and billing. Requires an account.
- [Sign in](https://transcrib.si/login.html) and [Create an account](https://transcrib.si/signup.html): email and password; no card needed for the Free plan.
- [About](https://transcrib.si/about.html): why the service exists, who writes the guides and how we work.
- [Security](https://transcrib.si/security.html): password and API key hashing, TLS, storage separation, file deletion, and how to report a vulnerability to security@transcrib.si.
- [Privacy policy](https://transcrib.si/privacy.html): data categories, purposes, processors, retention periods and how to exercise your rights.
- [Terms of service](https://transcrib.si/terms.html): plans and fair use, account rules, acceptable use, content rights, suspension, liability and the governing law.
- [Contact](https://transcrib.si/contact.html): support, security, legal, Team plans and API volume.

## API

- REST base URL: https://api.transcrib.si, versioned under /v1.
- Authentication: `Authorization: Bearer <access_token>` for a session, `X-API-Key: <key>` for an API key.
- Upload a file: `POST /v1/transcripts` with a multipart `file`, a `language` field (ru, en or auto) and a `diarize` field (true or false).
- Read a transcript: `GET /v1/transcripts/{transcript_id}` returns the text, the status, the segments with start_s and end_s, the speaker labels, the language and the duration.
- Export a transcript: `GET /v1/transcripts/{transcript_id}/export?format=txt|md|srt|vtt|csv|docx`.
- Errors use one shape: `{"error": {"code": "...", "message": "..."}}`.
- The MCP server exposes transcribe_audio, summarize_transcript, extract_actions and list_transcripts.

## Optional

- [Full text of the site](https://transcrib.si/llms-full.txt): the documentation of the service, the API, the plans, the limits and the privacy facts in one file.