BLUNVOICE

Voice understands speech, produces transcripts and reads text back out in a natural voice. That makes conversations, voice control and voice agents usable directly in BLUN or through an application of your own.

Try Voice View prices

VOICE · MEETINGIllustrative demo

SPEAKER 1

SPEAKER 2

Summary Tasks Appointments and deadlines

Listen. Understand. Speak.

Voice in, usable result out.

TranscriptDecisionsTasks

Turning conversations into results

Voice converts meetings, interviews, phone calls and voice notes into structured text. King turns them into decisions and tasks.

Turning conversations into results

Instead of a confusing sequence of individual words, the result is a transcript with meaningful paragraphs and a readable structure.

Depending on the workflow: speakers separated, timestamps assigned, key sections marked
Handoff to King for a summary, decisions, action items with owners, and deadlines
Also open questions and risks, a follow-up email, or a project management entry

Turn the conversation into a quote.Voice listens, King understands the goal.Remind me tomorrow about the follow-up.Done. The reminder is set.

Speak instead of typing

You dictate tasks, compose messages, and control BLUN by voice, on the go, in the workshop, or while out at an appointment.

Speak instead of typing

A spoken sentence can be handed off to a complete agent workflow: Voice recognizes the speech, King understands the goal, and the BLUN platform carries out the connected steps.

Dictate tasks and compose messages
Control BLUN by voice
Useful anywhere a keyboard is impractical

Natural speech output and Voice Agents

Voice speaks text naturally and handles conversations in real time: listening, responding, asking follow-up questions, taking actions.

Natural speech output and Voice Agents

The tone, speaking rate, and character of the output can be adapted to the use case.

Speech output: generates natural voices for finished applications
28 languages with matching accents and controlled emphasis
24 kHz streaming: transmits audio quickly and continuously
Real time: answers are already processed during the conversation

What you can say to Voice.

Speak the way you would to a colleague.

Examples, freely formulated

Voice · Task

›

›Transcribe this customer conversation and separate the speakers.

Voice is working …●Voice ready

Transcribe

Separate speakers

Voice · Task

›

›Create a summary of the team meeting with decisions and action items.

Voice is working …●Voice ready

Summary

Decisions

Tasks

Voice · Task

›

›Write this voice message as a professional email.

Voice is working …●Voice ready

Recognize speech

Draft an email

Voice · Task

›

›Read this guide aloud slowly and clearly.

Voice is working …●Voice ready

Speech output

Adjust pace

Voice · Task

›

›Build a voice assistant that can retrieve order information.

Voice is working …●Voice ready

Voice Agent

Retrieve information

Voice · Task

›

›Translate this voice message and speak the answer aloud.

Voice is working …●Voice ready

Translate

Speak the answer

When Voice fits, and where caution applies.

Use Voice when …

audio or spoken language has to be processed
meetings and conversations should be documented automatically
users without a keyboard should be able to work with BLUN
an application must be able to speak naturally
a real-time voice assistant is being developed
spoken content should trigger actions directly
texts should be made available as audio

Voice listens, King thinks ahead

a meeting becomes a summary, decisions, and action items with owners and deadlines
a spoken order becomes a plan: King reviews the starting point, plans, and executes the steps
a customer conversation becomes a quote, a follow-up email, and a reminder
Follow-up questions and results come back as speech if you want

More about King

Please check

For conversations that are critical in legal, medical or financial terms, transcripts and automatically derived decisions should be checked before they are used further. Background noise, indistinct speech and several people talking at once can all affect recognition.

View all models

The details.

Collapsed until you need them.

Speech-to-Text and Text-to-Speech

Voice combines AI speech recognition and natural speech output with the BLUN platform. The model converts conversations and audio files into text, structures spoken content and outputs written answers as natural speech.

Speech can be processed in both directions, and Voice can be used in real time, so that answers are already processed and output while a conversation is still running.

Transcribing conversations: typical use cases

Meetings and discussions, interviews and customer conversations, phone notes, voice messages, dictations, training sessions and presentations, audio and video content, as well as spoken work instructions.

The transcript can be passed to King automatically to turn it into decisions, tasks, summaries, or complete documents.

What can come out of a meeting

A short summary, a list of all decisions, tasks with responsible people, mentioned dates and deadlines, open questions and risks, a follow-up email, and a project management entry.

Voice delivers the spoken content. King processes it professionally and can analyze connections, dependencies, and consequences in complex meetings.

Speech output: what it is good for

Digital phone assistants, voice-controlled product help, reading texts and documents aloud, audio versions of articles and guides, accessible user interfaces, spoken status messages, interactive learning offerings, and voice agents for internal processes.

Real-time voice agents

In a voice agent, speech recognition, model intelligence, tools, and speech output are combined into an ongoing conversation. The user doesn’t wait for a fully processed audio file: the system listens, responds, asks follow-up questions, and takes action.

Such an agent can, for example, check the status of an order, prepare an appointment, take a support request, or explain information from an internal system. Depending on the task, King can handle the reasoning.

Usage by plan

Voice does not have a token context window comparable to that of King. In the free tier and in paid plans, usage is described in terms of speech features, such as audio minutes, maximum file length, transcription scope, speech output or real-time use.

Position in the model family

Voice is the shared speech layer of the BLUN platform. The model combines speech input, transcription, speech output and real-time interaction, and works directly with King, agents and tools.

Waitlist: no purchase, no charge.

from 19 €per month, annually from 15 € per month

Four plans: Starter, Pro, Pro Max, and Enterprise. All prices excl. VAT. All four plans are on the central BLUN waitlist. The audio services included in the plans are listed in the pricing overview. The full overview with all features is on the pricing page.

Compare all tiers

ONE ACCOUNT FOR THE ENTIRE WORKSPACE.

One account for everything in chat.blun.ai: Chat and Work, Sites, Code, images, and voice. Sign up for the right plan or start right away with BLUN Voice.

Try Voice