The speech API that knows who's talking
Re:WayAI turns real-world conversations into structured, speaker-attributed transcripts. State-of-the-art diarization, LLM speaker attribution and your own private library of enrolled voices — one API call away.
Relatively lower diarization error rate than the state-of-the-art open-source model, across four public benchmarks.
European languages in batch, 40 locales in real-time streaming — same pipeline, same speaker accuracy.
Source audio is deleted the moment processing completes. Deleted, not archived.
Free credit on every new account — about 525 hours of speaker-attributed transcription. Per-minute billing after that.
From raw audio to named speakers
One job, four stages. Each stage returns its results as soon as it finishes — you never wait for the whole pipeline to read the transcript.
Upload or stream
Send any common audio or video format — conversion is handled. Or stream 16 kHz PCM over a WebSocket for real time.
Accurate ASR
Word-level timestamps in 25 European languages, batch or streaming, built for conversational speech.
Who spoke when
State-of-the-art segmentation by voice — robust to overlap, crosstalk and far-field microphones.
Real names
An LLM reads the conversation and names each speaker — with confidence and quoted evidence — or matches voices you've enrolled.
Measured, not promised
Diarization error rate (DER) across four public benchmark corpora — real meetings and in-the-wild media. Identical audio, identical scoring for both systems. Lower is better.
| Benchmark | State-of-the-art open source | Re:WayAI | Rel. improvement |
|---|---|---|---|
| Dataset 1 Project meetings, multi-mic rooms | 17.05% | 13.39% | −21.5% |
| Dataset 2 Natural research meetings, up to ~10 speakers | 30.84% | 24.10% | −21.9% |
| Dataset 3 In-the-wild media: debates, talk shows, interviews | 11.14% | 8.61% | −22.7% |
| Dataset 4 Office meetings, single far-field device | 27.67% | 23.26% | −15.9% |
| Overall Average across all four | 21.68% | 17.34% | −20.0% |
DER — diarization error rate, lower is better. Internal evaluation, July 2026, on public diarization benchmarks (descriptions indicate each recording scenario), scored with the same protocol for both systems. Bottom line: 20% relatively fewer diarization errors than the state-of-the-art open-source model on average — and the advantage holds from clean media to far-field meeting rooms.
Built for the hard part: the speakers
Anyone can transcribe. We also get the speakers right.
Overlap-robust diarization
Segmentation that holds up on interruptions, crosstalk and far-field recordings — not just clean studio audio.
LLM speaker attribution
An LLM reads the conversation and puts real names on speakers — each with a confidence score and the quoted evidence behind it.
Advanced LLM capabilities
The LLM stage goes beyond naming: it repairs diarization slips, cleans segment boundaries and turns raw output into a readable transcript.
Real-time streaming
Live transcription over a WebSocket with partial results as words are spoken — straight from a microphone or a call.
Transcript Q&A
Ask questions about any finished transcript — “what did we decide on pricing?” — and the answer is grounded strictly in what was said.
25 European languages
English plus 24 more, through the same pipeline — same diarization, same attribution, same accuracy.
Your own database of voices
Enroll a voice once with ~10 seconds of audio. From then on, that person is recognized by name in every recording you send — before the LLM even has to guess.
- Private by design — your voice library belongs to your account alone; it is never shared or matched against anyone else's audio
- Messy samples welcome — enrollment audio is diarized first, and the dominant speaker becomes the profile
Your audio never outlives the job
Voice recordings are some of the most sensitive data there is. The pipeline is built around that fact — GDPR compliant and ISO 27001 certified, not audited into shape afterwards.
Audio deleted immediately
Source audio is deleted the moment processing completes. We never retain, reuse or train on your recordings — there is nothing left to leak.
ISO 27001, our own DC
Re:WayAI is ISO 27001 certified. Every job runs inside our own certified data center — your audio never leaves it, and no third-party cloud or AI API ever touches it.
Transcripts stay yours
Finished transcripts are stored for you until you delete them — retrieve, export or remove them at any time via the console or the API.
Audio can't leave the building at all?
The entire pipeline — models included — can be installed on your own hardware and run fully offline, behind your firewall.
Transparent pricing, pay as you go
We run our own hardware in our own ISO 27001 data center — no hyperscaler margin baked into every minute. That's exactly why we can undercut the big transcription APIs.
Speaker-attributed transcript with speaker names
The full pipeline in one API call: transcription, speaker diarization and LLM speaker naming — one price, billed per minute of audio.
- No subscriptions, no minimums — pay only for audio you process
- Or run any stage on its own: every job is billed per stage
- Live rates in the console, metered usage API included
then pay as you go — $0.19/hour all-in (2× Growth rates)
- ~525 hours of full speaker-attributed transcription on us
- Batch API, real-time streaming & transcript Q&A
- 25 languages batch · 40 locales streaming
- GDPR compliant, ISO 27001 certified
- No credit card to start
all-in — the rates in the table above
- 50% off Starter on every stage, committed volume
- Monthly or annual commitment, invoiced
- Priority support
- Same privacy guarantees: GDPR, ISO 27001
fully negotiable — built around your workload
- On-premise: the whole pipeline behind your firewall
- Custom SLAs and dedicated support
- Unlimited scale, custom integrations
- Zero data retention by design
Speak with our experts
Volume pricing, on-premise deployment, or just not sure which stages you need — tell us about your workload and we'll get back to you within one business day.
Message sent
Thanks — we'll get back to you within one business day.
A confirmation is on its way to your inbox.