Agents

Models

Resources

Pricing

Contact Sales

Pulse™

Speech to text that keeps up with the conversation

Turn live speech, calls, audio and video into structured text with 64ms model latency, 38+ languages, speaker labels and speech intelligence.

Start transcribing

Contact sales

Click anywhere to start transcribing

Experience pulse speech to text

Pulse™

Speech to text that keeps up with the conversation

Turn live speech, calls, audio and video into structured text with 64ms model latency, 38+ languages, speaker labels and speech intelligence.

Start transcribing

Contact sales

Click anywhere to start transcribing

Experience pulse speech to text

Pulse™

Speech to text that keeps up with the conversation

Turn live speech, calls, audio and video into structured text with 64ms model latency, 38+ languages, speaker labels and speech intelligence.

Start transcribing

Contact sales

Click anywhere to start transcribing

Experience pulse speech to text

What is Speech-to-text?

Speech to text converts spoken audio into written words that can be searched, analyzed, displayed as captions or used by an application.

Built for a useful next step, not just a response.

Transcription that keeps a finger on the Pulse™

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

Transcription that keeps a finger on the Pulse™

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

World’s Most Advanced Speech Intelligence

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

Emotion Recognition

Detects user emotions to make conversations more empathetic

Industry-Leading acccuracy and speed

Pulse STT outperforms the competition with the lowest Word Error Rates across 30+ languages and sub-70ms latency for seamless, real-time conversations.

Context Switching

Pulse adapts to healthcare, legal, finance, media, customer support, and enterprise.

Context Switching

Pulse adapts to healthcare, legal, finance, media, customer support, and enterprise.

Context Switching

Pulse adapts to healthcare, legal, finance, media, customer support, and enterprise.

Transcribe in 38+ languages

Delivering exceptional accuracy across accents, dialects, and recording conditions.

Transcribe in 38+ languages

Delivering exceptional accuracy across accents, dialects, and recording conditions.

Transcribe in 38+ languages

Delivering exceptional accuracy across accents, dialects, and recording conditions.

Speaker diarization for clarity

Identify transitions between speakers and accurately label each contribution

Speaker diarization for clarity

Identify transitions between speakers and accurately label each contribution

Speaker diarization for clarity

Identify transitions between speakers and accurately label each contribution

Follow every capability to its source

Review implementation details and evidence for accuracy, intelligence, language handling, speakers, redaction, and model choice.

Accuracy and latency

See the evaluation methodology, latency measurements, and accuracy results.

View Pulse benchmarks

Emotion detection

Go beyond words by returning emotional context with the transcript.

Explore emotion detection

Language detection

Automatically identify the language in incoming audio before downstream processing.

Explore language detection

Speaker diarization

Separate and label speakers in multi-speaker audio.

Explore speaker diarization

Sensitive-data redaction

Handle sensitive information in transcripts before it moves into downstream workflows.

Explore PII & PCI redaction

Pulse

Review the model card for current real-time use cases, capabilities, and release details.

View Pulse model details

Pulse Pro

Review the model card for current high-accuracy recorded-audio positioning.

View Pulse Pro model details

Our models

Speed or accuracy? you don't have to guess.

Our models

Speed or accuracy? you don't have to guess.

Our models

World’s Most Advanced Speech Intelligence

Pulse

Best for live audio, voice agents, and streaming transcription.

Live streaming & recorded

64ms ultra-low latency

38+ languages

~$0.005/min

Newly launched

Pulse Pro

Built for the highest transcription accuracy on recorded audio

Pre - recorded audio only

Max accuracy in transcription

Available only in English

~$0.004/min

Calculate your costs based on your usage needs

Select model

Select a model above to see pricing

Recommended plan

Pay as you go

Select a feature

No monthly commitments

Scale with your usage

Access to all features

Start building

Calculate your costs based on your usage needs

Select model

Select a model above to see pricing

Recommended plan

Pay as you go

Select a feature

No monthly commitments

Scale with your usage

Access to all features

Start building

Calculate your costs based on your usage needs

Select model

Select a model above to see pricing

Recommended plan

Pay as you go

Select a feature

No monthly commitments

Scale with your usage

Access to all features

Start building

Turn conversations into useful data

Build voice agents, captions, meeting notes, subtitles, call analytics, documentation, search and accessibility tools.

API

SDK

Visual tools

Talk to a builder

Start with a working request and API key setup in the Speech-to-Text quickstart

Need a full implementation path? Follow the Speech-to-Text API integration guide for Python, Node, and streaming.

01const res = await fetch(02  "https://api.smallest.ai/waves/v1/lightning-v3.1/get_speech",03  {04    method: "POST",05    headers: {06      Authorization: "Bearer YOUR_API_KEY",07      "Content-Type": "application/json",08    },09    body: JSON.stringify({10      text: "Modern problems require modern solutions.",11      voice_id: "magnus",12      sample_rate: 44100,13      output_format: "wav",14    }),15  },16);17 18writeFileSync("output.wav", Buffer.from(await res.arrayBuffer()));19console.log("Saved to output.wav");

01const res = await fetch(02  "https://api.smallest.ai/waves/v1/lightning-v3.1/get_speech",03  {04    method: "POST",05    headers: {06      Authorization: "Bearer YOUR_API_KEY",07      "Content-Type": "application/json",08    },09    body: JSON.stringify({10      text: "Modern problems require modern solutions.",11      voice_id: "magnus",12      sample_rate: 44100,13      output_format: "wav",14    }),15  },16);17 18writeFileSync("output.wav", Buffer.from(await res.arrayBuffer()));19console.log("Saved to output.wav");

Audio in. Structured text out.

Build real-time pipelines with Node and Python SDKs, without managing speech infrastructure or middleware.

Node SDK
Real-time pipelines
Python SDK
Backend workflows
Live streams
Voice agents and calls
Recorded audio
Media and archives

Speech intelligence for the next workflow

Follow the product or solution path that matches what you need to put into production.

Voice AI

Stream transcripts into conversational systems that need fast turn-taking.

Speech to text for voice AI

AI notetakers

Combine transcription, speaker separation, and timestamps for searchable meeting records.

Speech to text for AI notetakers

Call centers

Transcribe conversations for QA, analytics, and automation.

Planning a larger rollout? See speech to text for call centers at scale

Speech to text for call centers

Pay for the minutes you use

Choose the right model, scale with usage and estimate costs through the on-page calculator.

View Speech-to-Text pricing

Discuss deployment

Choose a model

Pulse or Pulse Pro

Set your usage

Minutes, not seats

Estimate cost

Before production

Scale as needed

No fixed workflow

Certified & Compliant

We listen and we don't tell.

View compliance

Certified & Compliant

We listen and we don't tell.

View compliance

ISO 27001

SOC 2 Type 2

GDPR Compliant

HIPAA Compliant

Proactive Defense

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

ISO 27001

SOC 2 Type 2

GDPR Compliant

HIPAA Compliant

Proactive Defense

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

ISO 27001

SOC 2 Type 2

GDPR Compliant

HIPAA Compliant

Proactive Defense

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

Frequently
asked questions

Can I try speech to text online?

Does Pulse work in real time?

Can it identify different speakers?

How many languages are supported?

Can I use Pulse for voice agents?

Explore the Speech-to-Text category

Go from the core transcription platform to a language, use case, or implementation guide without leaving the topic cluster.

Transcription by use case

Move into the workflow that best matches the audio.

Live captionsReal-time readable text for live experiences.

Podcast transcriptionTurn episodes into searchable transcripts.

Interview transcriptionCapture and organize multi-speaker interviews.

Medical transcriptionExplore transcription for healthcare workflows.

Meeting assistantsCreate structured meeting records.

Audio to textTranscribe files, calls, and recordings.

Speech recognition guides

Read the technical and evaluation resources behind production choices.

Best speech-to-text models in 2026Accuracy, latency, and production fit.

What makes a high-performance real-time ASR API?Streaming architecture and response behavior.

Streaming speech to text in productionDropouts, reconnects, and duplicate events.

How to evaluate ASRTest accuracy against the audio that matters.

Enterprise speech-to-text complianceHIPAA, SOC 2, and procurement considerations.

Turn every conversation into useful data.

Contact sales

311 California Street, Suite 320
San Francisco, CA 94104

Models

Text to Speech

Speech to Text

Speech to Speech

Voice cloning

Agents

Overview

On Prem

Products

LazyVoice

CapKit

Industries

Healthcare

Real Estate

Travel & Hospitality

Automobile

Banking

E-commerce

Documentation

For Agents

For Models

Resources

Pricing

Blogs

Research

Careers

Voice Library

Voice AI apps

Integrations

Dictionary

Press kit

Customers

Initiatives

Startup Grants

Legals

Privacy notice

Terms and conditions

Data processing

User Policy

TCPA compliance

Twitter

Instagram

Youtube

Discord

Substack

Medium

System status operational

We are

SOC 2,

GDPR, and

HIPAA, Compliant

Turn every conversation into useful data.

Contact sales

311 California Street, Suite 320
San Francisco, CA 94104

Documentation

For Agents

For Models

Resources

Pricing

Blogs

Research

Careers

Voice Library

Voice AI apps

Integrations

Dictionary

Press kit

Customers

Initiatives

Startup Grants

Twitter

Instagram

Youtube

Discord

Substack

Medium

System status operational

We are

SOC 2,

GDPR, and

HIPAA, Compliant

Turn every conversation into useful data.

Contact sales

311 California Street, Suite 320
San Francisco, CA 94104

Models

Text to Speech

Speech to Text

Speech to Speech

Voice cloning

Agents

Overview

On Prem

Products

LazyVoice

CapKit

Industries

Healthcare

Real Estate

Travel & Hospitality

Automobile

Banking

E-commerce

Documentation

For Agents

For Models

Resources

Pricing

Blogs

Research

Careers

Voice Library

Voice AI apps

Integrations

Dictionary

Press kit

Customers

Initiatives

Startup Grants

Legals

Privacy notice

Terms and conditions

Data processing

User Policy

TCPA compliance

Twitter

Instagram

Youtube

Discord

Substack

Medium

System status operational

We are

SOC 2,

GDPR, and

HIPAA, Compliant

Speech to text that keeps up with the conversation

Speech to text that keeps up with the conversation

Speech to text that keeps up with the conversation

What is Speech-to-text?

Transcription that keeps a finger on the Pulse™

Transcription that keeps a finger on the Pulse™

World’s Most Advanced Speech Intelligence

Follow every capability to its source

Speed or accuracy? you don't have to guess.

Speed or accuracy? you don't have to guess.

World’s Most Advanced Speech Intelligence

Pulse

Pulse Pro

Calculate your costs based on your usage needs

Calculate your costs based on your usage needs

Calculate your costs based on your usage needs

Turn conversations into useful data

Node SDK

Python SDK

Live streams

Recorded audio

Speech intelligence for the next workflow

Pay for the minutes you use

We listen and we don't tell.

We listen and we don't tell.

Frequently asked questions

Explore the Speech-to-Text category

Turn every conversation into useful data.

Turn every conversation into useful data.

Turn every conversation into useful data.

Frequently
asked questions