home hero

The Speech-to-Text
API for modern developers

Start building now
Contact sales
AssemblyAI is a top rated API for speech recognition, trusted by startups and global enterprises in production
CallRail LogoVoiceOps LogoLiine logo AssemblyAI Speech-to-Text APIOQ LogoMindstamp
Benchmark

See how AssemblyAI compares to Google, AWS, and other providers on your data

Compare now
Code samples

Designed for Developers

Stop struggling to understand messy APIs and SDKs - AssemblyAI makes it easy for any developer to quickly transcribe their audio and video content
View the API Docs
AssemblyAI Speech-to-Text API consoleAssemblyAI Speech-to-Text API console 3AssemblyAI Speech-to-Text API console 4AssemblyAI Speech-to-Text API console 5AssemblyAI Speech-to-Text API console 1AssemblyAI Speech-to-Text API console 2
Features

An API for more than just Speech Recognition

See all features
AssemblyAI Speech-to-Text API speaker diarization
Speaker Diarization
Know who spoke when
AssemblyAI Speech-to-Text API PII redaction
PII Redaction
Detect and remove credit card numbers, SSNs, and more
AssemblyAI Speech-to-Text API automatic transcript highlights
Automatic Transcription Highlights
Surface the most common keywords and phrases
AssemblyAI Speech-to-Text API 99% uptime
99.9%+ Uptime
Trusted in production to handle millions of transcriptions each day
AssemblyAI Speech-to-Text API model customization
Model Customization
On-the-fly add keywords and phrases unique to your application or customers
AssemblyAI Speech-to-Text API entity detection
Entity Detection
Detect things like names, injuries, and places spoken in the text
AssemblyAI Speech-to-Text API speaker diarization
Advanced Security and Data Privacy Protocols
We never store your data, and follow strict security protocols within our systems
AssemblyAI Speech-to-Text API blue strip
Why AssemblyAI

We’re a Deep Learning company, obsessed with moving the State of the Art forward, and giving developers access to great AI tech

High Performancer Fall LogoBest Public API Logo
Fastest-improving accuracy
Our research team deploys accuracy improvements weekly, and is constantly pushing the State of the Art.
In-house research team
We conduct our own research, and publish leading papers and blogs about the state of Automatic Speech Recognition.
99.9+ uptime
Our systems operate with 99.9%+ uptime and are highly scalable and redundant.
More than Speech-to-Text
Top-rated accuracy along with sentiment analysis, PII redaction, entity recognition, summarization, and more.
Product
FeaturesAPI DocsAPI StatusReport Vulnerability
Customers
TelephonyVideo PlatformsPodcast PlatformsMedia MonitoringVirtual MeetingsStartups
Compare
Benchmark AssemblyAI
AWS Transcribe
Google Speech-to-Text
About
Company
Blog
Terms
Privacy
Careers