APPLICATION FEATURES

From meeting transcription to decisions with local AI.

Promic Speech AI is a Windows application for documenting meetings, reviewing what was said and consulting meeting history. In the Professional edition, AI processing and the archive stay on the customer workstation. Archive features depend on the selected usage profile and settings.

Start a free 15-day trial
Live transcription — editor and speaker identification
Live transcription — editor and speaker identification. Real Promic Speech AI screenshots, captured with an Enterprise license. The features shown (transcription, review, Decision Center, commitments and chat) are also in Professional; Enterprise adds users, groups and permissions in a shared archive, models larger than 32 GB and AI processing centralized on a server.
01

Your AI, in your infrastructure

In Professional, transcription, summaries and queries process content on the Windows workstation. Activation and model downloads use the internet.

02

Enterprise for teams

Users, groups and permissions in an organizational archive, AI models larger than 32 GB and AI processing centralized on a server. Deployment by proposal.

03

Chat with your archive

Ask AI questions, request summaries and suggested next steps. Check the cited meetings before acting.

FEATURE COMPARISON

What you can do in each edition.

Open a feature for details. Archive steps also depend on the selected usage profile and analysis settings.

Swipe the table to compare editions.

What you can do in each edition.
FeatureProfessionalEnterpriseGovernment
Capture and transcription
Microphones and USB interfaces

Transcribe in-person meetings live from an audio device.

IncludedIncludedIncluded
Window audio

Capture an online call from a selected window without joining as a bot.

IncludedIncludedIncluded
NDI capture

Receive audio and video over the network, such as in chambers and studios.

IncludedIncludedIncluded
Two capture channels

Use two sources at once, each a microphone, a call window or NDI.

IncludedIncludedIncluded
Audio and video files

Transcribe recordings in formats including WAV, MP3, MP4 and WebM.

IncludedIncludedIncluded
MP3 or MP4 recording

Record MP4 video (1080p, 720p or 360p) or MP3 audio during live transcription; turned on in Settings.

IncludedIncludedIncluded
Local Whisper models

Large V3 Turbo is the default; the catalog adds Large V3, Medium and Medium English for English-only audio.

IncludedIncludedIncluded
Language independent of interface

Choose the spoken language without changing the menu language.

IncludedIncludedIncluded
Noise suppression

Adjust NVIDIA Maxine noise reduction intensity.

IncludedIncludedIncluded
Replacement dictionary

Automatically correct recurring names, acronyms and terms.

IncludedIncludedIncluded
Reusable text blocks

Insert prepared text blocks while editing.

IncludedIncludedIncluded
Automatic saving

Recover the document if the computer shuts down mid-session.

IncludedIncludedIncluded
Speakers
Up to 50 speakers separated

Separate speech by voice after entering the estimated participant count.

IncludedIncludedIncluded
Voice profiles

Create a profile for each identified voice and save recurring speakers for future meetings.

IncludedIncludedIncluded
Names from what is said

A local model understands phrases such as "I give the floor to John" or "my name is…" and names the passage.

IncludedIncludedIncluded
Participant corrections

Rename (updates the whole document), mute (leaves that person out of the text) or drag one speaker onto another to merge them.

IncludedIncludedIncluded
PROMIC chamber integration

Identify the speaker from the open desk microphone and, optionally, transcribe only during the speaking time.

Not includedBy proposalBy proposal
Review and documents
Review with player

Listen beside the text at 0.25x to 2x speed, with 10 s back and 30 s forward.

IncludedIncludedIncluded
Time links

With recording on, @hh:mm:ss links in the text take the player to that moment, while the file remains accessible.

IncludedIncludedIncluded
Full text editor

Formatting, tables, headers and footers, table of contents, spell check in English, Portuguese and Spanish, password protection and printing.

IncludedIncludedIncluded
Comments and tracked changes

Review a document with comments and a record of edits.

IncludedIncludedIncluded
Minutes and session templates

Minutes template with automatic fields, plus chamber events: opening, roll call, voting, result and closing.

IncludedIncludedIncluded
DOCX and PDF export

DOCX from the editor and the archive; PDF from the archive.

IncludedIncludedIncluded
AI, archive and management
Meeting summaries

Create a summary with a local language model and review it before sharing.

IncludedIncludedIncluded
Qwen and Gemma models for summaries and chat

Choose from Qwen and Gemma model families in the catalog, subject to GPU and edition.

IncludedIncludedIncluded
Editable styles and instructions

Detailed, executive minutes, action-focused, chronological by topic, court hearing minutes and more; edit or create styles.

IncludedIncludedIncluded
Document summaries

Summarize DOC, DOCX and TXT files outside the archive workflow.

IncludedIncludedIncluded
Decision and reversal extraction

Extract the meeting’s decisions and record when a later meeting reverses them.

IncludedIncludedIncluded
Commitment extraction

Review suggested actions, owners and due dates; accepted ones become pending items for the next meeting.

IncludedIncludedIncluded
Disagreement extraction

Record unresolved differences and track their outcome.

IncludedIncludedIncluded
Open questions and closeout

Optional: record each meeting’s objective, outcome and the questions left open.

IncludedIncludedIncluded
Connections across meetings

Compare each meeting with earlier ones on the same topic, close old pending items and record reversals.

IncludedIncludedIncluded
Written analysis

4 to 8 critical points, why they matter and who should act; checks flag unsourced values and dates and totals that do not add up.

IncludedIncludedIncluded
Decision Center

Queue of what needs attention (overdue, blocked, pending condition, disagreement), a timeline and the statement behind each item.

IncludedIncludedIncluded
Commitment kanban

View by attention or by owner; complete, cancel, reassign or change the due date.

IncludedIncludedIncluded
Meeting archive

Browse transcripts, summaries and analyses by meeting and topic.

IncludedIncludedIncluded
Chat with sources

Ask the archive in plain language; citations open the source meeting.

IncludedIncludedIncluded
Archive search and filters

Filter by period and topic; semantic search needs the meetings indexed first.

IncludedIncludedIncluded
Infrastructure and access
AI in customer infrastructure

Content is processed on a workstation or customer server, by edition.

IncludedIncludedIncluded
PostgreSQL archive with pgvector

Keep archive data in customer infrastructure.

IncludedIncludedIncluded
Multiple users and groups

Manage users, groups and organizational units.

Not includedIncludedIncluded
Permissions and visibility

Control actions and meeting access by user, group and unit.

Not includedIncludedIncluded
Archive on a network server

Share an archive database within the organization.

Not includedIncludedIncluded
Models larger than 32 GB

Use the expanded model catalog with suitable hardware.

Not includedIncludedIncluded
Centralized server AI

Centralize GPU and models on a server in the contracted architecture.

Not includedIncludedBy proposal

Enterprise and Government are configured by proposal. Government AI processing may run on each workstation or on a server. Integration with a PROMIC chamber system depends on the project.

COMPATIBLE MODELS

Choose AI models in the application.

Promic Speech AI uses Whisper for transcription and local third-party models for other tasks. In Settings, choose an installed model for transcription, speaker labels, summaries and chat; the in-app catalog offers compatible files for download.

Transcription · Whisper (ggml .bin)

Whisper Large V3 Turbo (default), Large V3, Medium Q8, Medium English Q8 and Small.

Medium English Q8 is for English audio only.

Summaries, chat and speaker labels · GGUF

Qwen3.5 4B, 9B, 35B-A3B and 122B-A10B; Qwen3.8 27B; Gemma 4 E4B, 12B, 26B-A4B and 31B; GPT-OSS 20B.

The catalog identifies the role of each variant; for example, Qwen3.5 4B is offered for speaker labels.

Archive search · GGUF

Qwen3-Embedding-0.6B Q8_0 and BGE Reranker v2 m3 Q8_0.

Supporting models for indexing, search and result ranking.

These are third-party models downloaded through the in-app catalog. Availability depends on the installed version, NVIDIA GPU, video memory, edition and file variant. Compatibility of external files outside the catalog is not guaranteed.

See the full list and how to choose ↗
01

Capture in-person meetings and online calls

Transcribe live through a room microphone or USB audio interface without a video meeting platform. For online calls, the application can capture audio from a selected window without adding a meeting bot. You can also open existing audio or video files.

02

Choose a transcription model

Whisper Large V3 Turbo is the default. The catalog also includes Large V3, Medium Q8 and Medium English Q8, the last of these for English audio. Availability and performance depend on the GPU and installed models.

03

Separate up to 50 speakers and create voice profiles

Set the estimated number of participants before the meeting, and the application separates speech by voice for up to 50 people. This speaker diarization creates a profile for each identified speaker. You can save recurring participants’ voices to recognize them in future meetings, correct assignments and merge duplicate voices. With clear audio, speaker identification is highly accurate; overlapping speech and similar voices may require review.

04

Review text and export documents

The transcript appears in an integrated editor. When the recording is available, review can return to the audio passage related to a statement. The reviewed document can be exported as DOCX or PDF.

05

Create summaries with local models

Choose Qwen, Gemma or GPT-OSS models from the catalog, subject to GPU and edition, and use styles such as executive minutes, detailed, action-focused or chronological by topic. Summary instructions can be edited. Review names, numbers and conclusions before sharing.

06

Chat with AI about your meetings

For chat, you can also choose GGUF models compatible with your GPU and edition. Ask questions in natural language, request a summary of a meeting or period, and ask for suggested next steps grounded in the archive. Chat consults available transcripts, summaries and facts according to the usage profile, with references to source meetings. Check the sources and review suggestions before acting. Semantic search requires prior indexing.

07

Follow decisions and commitments

When fact analysis is enabled, the application organizes suggested decisions, disagreements and commitments. A person reviews and accepts these items; the Decision Center brings together open items and shows context from related meetings.

08

Build local infrastructure without cloud AI processing

In Professional, the GPU, AI models and archive database reside on the Windows workstation: meeting content need not be sent to a cloud AI service for transcription, summaries or archive queries. In Enterprise, archive and access can reside in the organization’s infrastructure as defined in the proposal. License activation and initial model downloads use the internet.

09

Connect your team with Enterprise

An Enterprise deployment connects multiple users to the organization’s archive, with groups and permissions for each role. AI processing can be centralized on a server, with models larger than 32 GB. Capacity and the number of simultaneous meetings are defined in the proposal.