customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Universal 3.5 Pro
Our new flagship speech-to-text model handles real-world audio the way it actually happens. Available for real-time and pre-recorded audio.
resources
Install the SDK, create a client with your API key, and await a single transcribe call—fully typed, promise-based, and it polls for you. Start free, no credit card.
Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US.
Skylines from Maine to Maryland to Minnesota are gray and smoggy.
Officials are urging residents to stay indoors where possible.
npm install assemblyai adds typed speech-to-text to any Node or TypeScript project.
Await a single transcribe call and get a typed result back—the SDK handles upload and polling for you.
Full TypeScript types on the transcript object mean autocomplete on text, utterances, and entities.
36%
improvement in close rate
“The new Universal-3.5 Pro speech model from AssemblyAI is best so far in terms of accuracy, latency, and language switching.”
80%
increase in customer satisfaction
“Assembly has saved us countless hours managing models, and provided exceptional accuracy.”
36%
improvement in close rate
“The new Universal-3.5 Pro speech model from AssemblyAI is best so far in terms of accuracy, latency, and language switching.”
80%
increase in customer satisfaction
“Assembly has saved us countless hours managing models, and provided exceptional accuracy.”
Set your API key as an env var, run npm install assemblyai, and paste a few lines into a script. Run it and the transcript prints—no servers, no manual polling loop.
Start building freeNo credit card required
Word error rate is the share of words the model gets wrong against a human reference—the standard measure of transcription accuracy on pre-recorded audio.
Pre-recorded word error rate on English audio.
*Lower is better*Source: AssemblyAI published benchmarks — assemblyai.com/benchmarks.
