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, drop in your API key, and transcribe a file with one call—the SDK handles upload, submission, and polling 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.
And in some places, the air quality is dropping to unhealthy levels.
A single pip install adds production speech-to-text to your Python project—no other dependencies to set up.
Transcriber().transcribe() uploads, submits, and polls in a single line, so there's no queue plumbing to write.
Flip on speaker labels, language detection, or entity detection by setting one option on the same request.
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.”
Grab a free API key, run pip install assemblyai, and paste a few lines into a script. Run it and your transcript prints to the terminal—no infrastructure, no async queue to manage.
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.
