# Dialogist > AI voice agents that listen, think ahead and get things done on your phone lines: bookings, reminders and follow-ups in 48 languages, one fixed price per agent. ## Key pages - [Home / waitlist](/en/): AI voice agents that listen, think ahead and get things done on your phone lines: bookings, reminders and follow-ups in 48 languages, one fixed price per agent. - [Markdown twin of this page](/en.md) - [Pricing: per agent, not per minute](/en/pricing/): Each Dialogist agent costs a fixed amount a month, like an employee on a salary. Minutes are not billed, so a busy month does not raise the price of the agent. To take more calls, add an agent. - [Solutions overview](/en/solutions/) - [Voice Agents](/en/solutions/voice-agents/): Answer calls 24/7, book appointments and run reminders, without code or a phone system to install. - [Platform](/en/solutions/platform/): Agents, knowledge, telephony, queues, campaigns, analytics and integrations in one platform. - [Enterprise](/en/solutions/enterprise/): Full on-premise deployment on our own and open-weight models, dedicated installations, and hands-on AI and ML consulting. - [Incoplax](https://incoplax.com/): Telecom infrastructure for voice products: numbers, SIP trunks, routing and carrier relationships. - [Use cases](/en/use-cases/): Six jobs an AI voice agent does on your phone lines: reception and booking, order confirmation, payment reminders, candidate calls, lead follow-up and surveys. - [Receptionist & booking](/en/use-cases/receptionist/): An AI voice receptionist that answers your calls, books, moves and cancels appointments in your schedule, and passes the difficult calls to your team. - [Order confirmation](/en/use-cases/order-confirmation/): An AI voice agent that calls your customers to confirm an order, check the delivery address and time, and record the result in your system. - [Payment reminders](/en/use-cases/payment-reminders/): An AI voice agent that reminds customers about payments, agrees a date and an amount, and records the promise to pay in your system. - [Candidate calls](/en/use-cases/candidate-calls/): An AI voice agent that calls applicants, asks your questions, answers theirs about the role and books interviews with your recruiters. - [Lead follow-up](/en/use-cases/lead-follow-up/): An AI voice agent that calls new leads back within minutes, asks your qualifying questions and books a meeting or transfers the call to sales. - [Surveys](/en/use-cases/surveys/): An AI voice agent for phone surveys: NPS, satisfaction and feedback calls, with follow-up questions and the same structured fields from each call. - [Integrations](/en/integrations/): Connect Dialogist AI voice agents for phone calls to Salesforce, Creatio and Zendesk out of the box, or to any system with an API. - [Technologies](/en/technology/): How a Dialogist AI voice agent answers phone calls in about a quarter of a second, keeps listening while it talks and finds answers in your documents. - [Languages](/en/languages/): Dialogist AI voice agents hear and speak 48 languages on your phone lines. Every language has a hearing grade, from A++ down, measured in phone quality. - [Roadmap](/en/roadmap/): What the Dialogist team has shipped, what it is working on now and what is planned: recognition, voice, knowledge, testing and telephony. - [Trust & data](/en/trust/): Where Dialogist phone calls and data live, who can see them, what an AI voice agent may do in your systems, and how to report a vulnerability. - [Partners](/en/partners/): The companies Dialogist works with in telephony and CRM: Incoplax, 3CX and Creatio. System integrators, operators and agencies can join. - [About](/en/about/): Who builds Dialogist AI voice agents for phone calls: a team with decades in telephony and real-time systems, and the AI team that grew out of it in 2025. - [Privacy Policy](/en/privacy/): What dialogist.cc collects, why, how long we keep it and who sees it: the waitlist, analytics, cookies and the Try it live demo. - [Terms of Use](/en/terms/): The terms for using dialogist.cc: who runs it, what it offers, the Try it live demo, rights to our materials, liability and governing law. - [News](/en/news/): Product news from Dialogist: releases and platform changes, plus research notes from the team on how our voice agents perform on real calls. - [Oasis Speech 2: our agents now hear 48 languages](/en/news/oasis-speech-2-is-live/): 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. - [Deda Mraz is calling: Santa talks to children in Serbia, voiced by a Dialogist agent](/en/news/deda-mraz-is-calling/): 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. - [Cadence is public: the workbench we train Oasis Speech in](/en/news/cadence-is-public/): 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. - [Twelve questions to ask a voice AI vendor](/en/news/questions-for-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. - [Use cases, integrations and languages, now on the site](/en/news/use-cases-integrations-and-languages/): Six use cases with example calls, Salesforce, Creatio and Zendesk connectors, 48 languages and a look at the technology. What is new on dialogist.cc. - [Research](/en/research/): Research notes from the Dialogist team: latency, turn-taking, speech recognition and synthesis, measured on real calls and explained step by step. - [Voicecore: Rust media backend, road to infinite scalability with no idle GPUs](/en/research/voicecore-rust-media-core/): 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. - [One Server Unit: 100 simultaneous calls, load-tested to 176% of rated capacity](/en/research/server-unit-under-load/): 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. - [Oasis Speech 2: recognition in 48 languages, before and after](/en/research/oasis-speech-2/): Oasis Speech 2 lowers the error rate on short replies by 44% across the 48 languages it recognizes, and all 48 improve. - [Listening while talking, and what the agent does with the caller's open channel](/en/research/listening-while-talking/): How a Dialogist agent keeps listening while it speaks, starts its reply inside the pause and tells an interruption from a cough. - [The shortest answers are the hardest to recognize, and the most common on a call](/en/research/short-replies/): 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%. - [How we grade a conversation between a voice agent and a simulated caller](/en/research/how-we-grade-a-conversation/): Polygon, our test bench, grades a voice agent on whole conversations, with simulated callers, eight weighted criteria, hard gates and behavior probes. - [Cadence: the workbench where we fine-tune, evaluate and gate the models behind Oasis Speech](/en/research/cadence/): 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. - [What happens to a sentence after the voice model speaks it](/en/research/after-the-voice-model/): Between the voice model and the caller, the agent trims, resamples, checks and caches every sentence, and re-checks the cache at night. - [Knowing when the caller has finished](/en/research/knowing-when-the-caller-has-finished/): Across nearly 100,000 caller turns, our end-of-turn model closed most turns before the silence timer and gave back about 0.3 s per turn on real calls. ## Optional - [Full text (`llms-full.txt`): everything below, concatenated.](https://dialogist.cc/llms-full.txt) ## Notes - Last updated: 2026-11-11 - Content language: en