News
Product news and research notes from the Dialogist team.
Releases, platform changes and measurements from the team building Dialogist voice agents.
Voicecore: Rust media backend, road to infinite scalability with no idle GPUs
The Python media path used up the processor of one bot process at about 96 conversations. Voicecore, written in Rust, carries 224 with the GPU out of the way.ReadOasis Speech 2: our agents now hear 48 languages
Oasis Speech 2, the new version of our own speech recognition, is live. It hears 48 languages, and every one of them improved on short replies.ReadOne Server Unit: 100 simultaneous calls, load-tested to 176% of rated capacity
We loaded one Server Unit from a single call to 176% of its rated 100 calls. Replies held the Standard grade up to rated capacity, and every call connected.ReadDeda Mraz is calling: Santa talks to children in Serbia, voiced by a Dialogist agent
This New Year, Deda Mraz talks with children in Serbia in Serbian, in the browser or by phone. Free of charge, run on Dialogist's voice stack.ReadOasis Speech 2: recognition in 48 languages, before and after
Oasis Speech 2 lowers the error rate on short replies by 44% across the 48 languages it recognizes, and all 48 improve.ReadCadence is public: the workbench we train Oasis Speech in
We have published Cadence, the workbench where we train and evaluate the models behind Oasis Speech: a fork of our production system, under the MIT license.ReadListening while talking, and what the agent does with the caller's open channel
How a Dialogist agent keeps listening while it speaks, starts its reply inside the pause and tells an interruption from a cough.ReadTwelve questions to ask a voice AI vendor
The twelve questions that show whether a voice agent works on a real phone line or only in a sales meeting, with the answer we give to each.ReadThe shortest answers are the hardest to recognize, and the most common on a call
Most of what a caller says is a few words, and a few words are the hardest case for speech recognition. Oasis Speech 2 cuts errors on one-word replies by 49%.ReadHow we grade a conversation between a voice agent and a simulated caller
Polygon, our test bench, grades a voice agent on whole conversations, with simulated callers, eight weighted criteria, hard gates and behavior probes.ReadCadence: the workbench where we fine-tune, evaluate and gate the models behind Oasis Speech
Cadence is where we fine-tune and evaluate the models behind Oasis Speech. People and coding agents use one API, and every model must pass a gate.Read
Next step
Get early access to Dialogist voice agents: we invite teams from the waitlist as capacity opens.
Join the waitlist
We're letting teams in gradually. We'll email you when your spot opens.