# Speech Revolutions

> Batch speech-to-text API. Transcription with speaker diarization, word-level timestamps and
> automatic language detection, priced per audio minute with no add-on fees.

## What it is

- Batch transcription over HTTP. Upload audio, get a transcript with diarized speaker turns
  and word-level timestamps. Not a real-time or streaming product.
- One model, "zephyr". Automatic language detection across 99+ languages,
  including mid-file language switching.
- Output as JSON, TXT, SRT, VTT, DOCX or PDF from a single call.
- Official SDKs for Python, JavaScript/TypeScript, Go and C#.

## Pricing

- $0.003 per audio minute — $0.18 per audio hour.
- Diarization, word timestamps and repunctuation are included, not add-ons.
- $10 of credit on signup. Prepaid credits; no subscription and no minimum.

## Limits

- Up to 10 GB per file through the SDK, 200 MB through the direct REST endpoint.
- Audio and transcripts are deleted within 30 minutes of job completion.
- Customer audio is never used to train models.

## Measured results

Measured by Speech Revolutions on public datasets, last run 2026-07. Lower is better.

- Diarization error rate: 9.7% on AMI-SDM, 10.9% on NotSoFar, at a 0.25 s collar,
  overlap-aware. Best competitor measured: 25.3% and 23.3%.
- Word error rate: 2.54% on SPGISpeech.
- Timestamp start error: 40 ms mean absolute error.
- Methodology and the reproducible harness: https://docs.speechrevolutions.com/benchmarks

## For integrators

- Documentation: https://docs.speechrevolutions.com
- Machine-readable OpenAPI 3.1: https://docs.speechrevolutions.com/openapi.json
- Every docs page as Markdown: append `.md` to its URL
- Docs index for agents: https://docs.speechrevolutions.com/llms.txt
- Authenticate with an `X-API-Key` header against https://api.speechrevolutions.com

## Questions

### How is this different from Deepgram or AssemblyAI?

We focus exclusively on batch transcription, with transparent per-minute pricing and no add-on fees for diarization, timestamps, or repunctuation. If you process large volumes and want fast batch turnaround at a lower cost, we're built for that.

### Do you offer live streaming transcription?

Not at launch. Speech Revolutions is batch-only today — upload audio, track progress via SSE, download structured output. Live streaming is on the roadmap.

### What's the difference between Standard and Economy tiers?

Standard runs on dedicated compute, and most files come back in seconds. Economy is not available yet: when it ships it will use idle capacity at ~$0.09/hr with a 24-hour delivery SLA or explicit failure notification, for large backlogs where cost matters more than speed.

### Do you train on my audio?

No. We do not use customer audio to train speech recognition models. Uploaded files and transcripts are deleted within 30 minutes of job completion.

### What output formats are supported?

JSON (with word timestamps and speaker labels), TXT, SRT, VTT, DOCX, and PDF — all from a single API call.

### How large can uploads be?

Up to 200 MB via direct REST upload, or up to 10 GB through the SDK using presigned multipart uploads.

## Pages

- [Home](https://www.speechrevolutions.com/): product, benchmarks, pricing, live demo
- [Roadmap](https://www.speechrevolutions.com/roadmap): what is live and what is coming
- [Contact](https://www.speechrevolutions.com/contact)
- [Terms](https://www.speechrevolutions.com/terms) · [Privacy](https://www.speechrevolutions.com/privacy) · [Acceptable use](https://www.speechrevolutions.com/acceptable-use)