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
Speak to your app and have it speak back. AssemblyAI's Voice Agent API manages the full real-time loop—speech recognition, LLM reasoning, and voice—over a single WebSocket, so you don't stitch together separate providers.
Hey, can you check where my order #48217 is?
Let me look—it shipped yesterday and arrives Friday.
Great, can you text the tracking link to my phone?
Stream a user's voice in and get a spoken reply back over one connection, with interruptions handled for you.
Turn detection and low-latency streaming keep the back-and-forth feeling like a conversation, not a walkie-talkie.
The loop is built on AssemblyAI's real-time speech recognition, so the words feeding your model are right the first time.
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.”
Create an agent with a single API call and connect over one WebSocket—speech recognition, reasoning, and voice are already wired together, so your first real-time exchange happens in minutes. Try it in the playground with no code first.
Start building freeNo credit card required
A speech-to-speech loop is only as good as the words it hears. Streaming word error rate measures real-time transcription accuracy at the front of the loop against a human reference—errors here compound through reasoning and the spoken reply.
Streaming word error rate on English audio.
*Lower is better*Source: AssemblyAI published benchmarks — assemblyai.com/benchmarks.
