Skip to main content
This page lists what is coming, in the order we expect to ship it. The dates are targets, not contracts. A date moves when call quality demands it, and we choose quality over the date every time. Before you plan a launch around a row on this page, confirm it with your account contact.

​
Post-call analytics everywhere

Every call on every tier can get an AI summary and a QA score. The capability is part of every tier. In the v2 API, turn on analysis on an agent: the result is on the call, at GET /v2/calls/{id}/analysis and in the call.processed webhook, and it can pick the follow-up message template to send after the call.

​
Warm transfer everywhere

Transfer to a human is not available yet, and it has no date. The plan is for an agent on any tier to hand a call to a person at a number you set per agent. A call that ends this way will report ended_reason: transferred.

​
Model APIs

The models behind our calls also work on their own, for teams that want them without the telephony. Text to speech, speech to text in ten Indian languages, over HTTP or a WebSocket, and offline transcription are live today. The call-tuned LLM comes next. Each one takes the same sk_live_ key as the rest of v2, and the Speech API page lists them on one screen.

​
New TTS languages

Gujarati, Tamil and Telugu are live on the speech endpoint today, next to Hindi, English and Hinglish, and Mira STT transcribes all three. Kannada, Malayalam, Marathi and Bengali are in beta on all six voices. Gujarati, Tamil, Telugu, Kannada, Marathi and Bengali alone are the mother tongue of 429 million people, and most of them can’t be reached in Hindi at all. The language roadmap has the full story and the data.

​
Next-generation TTS

The next revision of the voice engine has lower first-audio latency and sounds more natural on Hindi and code-switched speech. It replaces the engine under every tier once it clears our quality bar. The API does not change, so your calls simply start sounding better.

​
Orchestration platform

The orchestration platform puts node graphs on a canvas, so you can build, test and version call flows visually. These are the same graphs that node-based agents run on every tier, but your ops team can author them instead of your engineers. Validation runs as you draw, and every published version is immutable, so a live campaign never runs an unreviewed edit.

​
New voices

The catalogue grows every month from August 2026. New voices appear in the voice gallery as they clear evaluation. Listen to a new voice in Agent Studio before you switch, because the choice of voice moves answer-through rates more than prompt wording does.

​
Channels

Calls will connect to other channels, starting with email follow-ups triggered by call outcomes (“summary of what we agreed”, “payment link after a confirmed order”). Other channels come after that. The design has the call outcome trigger each follow-up, so nobody has to send it by hand.