Speech to Text for Medical Transcription

Pulse transcribes medical conversations with accurate terminology and HIPAA-compliant processing.

Click anywhere to start transcribing

Experience pulse speech to text

Speech to Text for Medical Transcription

Pulse transcribes medical conversations with accurate terminology and HIPAA-compliant processing.

Click anywhere to start transcribing

Experience pulse speech to text

Speech to Text for Medical Transcription

Pulse transcribes medical conversations with accurate terminology and HIPAA-compliant processing.

Click anywhere to start transcribing

Experience pulse speech to text

Transcription Benchmarks

Transcription Benchmarks

Transcription Benchmarks

Model
Streaming
Batch
Smallest
3.1% WER
2.7% WER
Scribe v2
5.5% WER
4.8% WER
Deepgram
7.5% WER
6.6% WER
Whisper large v3
5.0% WER
4.4% WER

World’s Most Advanced Speech Intelligence

Go beyond text with automated speaker labeling, real-time sentiment analysis, and intelligent language identification for global production workloads.

World’s Most Advanced Speech Intelligence

Go beyond text with automated speaker labeling, real-time sentiment analysis, and intelligent language identification for global production workloads.

World’s Most Advanced Speech Intelligence

Go beyond text with automated speaker labeling, real-time sentiment analysis, and intelligent language identification for global production workloads.

For Developers

Automate. Orchestrate. Dominate with code

Build real-time speech pipelines with Node and Python SDKs. Audio in, transcription out — no middleware, no complexity.

For Developers

Automate. Orchestrate. Dominate with code

Build real-time speech pipelines with Node and Python SDKs. Audio in, transcription out — no middleware, no complexity.

For Developers

Automate. Orchestrate. Dominate with code

Build real-time speech pipelines with Node and Python SDKs. Audio in, transcription out — no middleware, no complexity.

01// Node.js 18+. This sample transcribes English audio with Pulse.02// Use your own audio and a documented language code for other languages.03const audioResponse = await fetch("https://github.com/smallest-inc/cookbook/raw/main/speech-to-text/getting-started/samples/audio.wav");04if (!audioResponse.ok) throw new Error(await audioResponse.text());05const audio = await audioResponse.arrayBuffer();06const response = await fetch("https://api.smallest.ai/waves/v1/stt/?model=pulse&language=en", {07 method: "POST",08 headers: {09 Authorization: `Bearer ${process.env.SMALLEST_API_KEY}`,10 "Content-Type": "application/octet-stream",11 },12 body: audio,13});14if (!response.ok) throw new Error(await response.text());15console.log((await response.json()).transcription);

Certified & Compliant

Guarding your data with enterprise security

Certified & Compliant

Guarding your data with enterprise security

Certified & Compliant

Guarding your data with enterprise security

Proactive Defense

Anticipating threats before they emerge, thanks to our advanced monitoring.

Proactive Defense

Anticipating threats before they emerge, thanks to our advanced monitoring.

Proactive Defense

Anticipating threats before they emerge, thanks to our advanced monitoring.

Frequently
asked questions

Is Pulse HIPAA compliant?

Can we keep patient audio inside our own infrastructure?

Are transcripts accurate enough for clinical and legal records?

Can Pulse tell the clinician apart from the patient?

Does it handle patients who switch languages mid-conversation?

Can we transcribe live during a consult as well as after it?

Languages

From your city to Timbuktu,
we hear you.

Languages

From your city to Timbuktu,
we hear you.