Voice Assistant | AI Speech Recognition

$ 17.31

v 19.0 Third Party

Availability	Odoo Online Odoo.sh On Premise
Lines of code	2123
Technical Name	`pys_voice_assistant`
License	LGPL-3
Website	https://odoo.pysquad.com

You bought this module and need support? Click here!

Availability	Odoo Online Odoo.sh On Premise
Lines of code	2123
Technical Name	`pys_voice_assistant`
License	LGPL-3
Website	https://odoo.pysquad.com

Pysquad

Community Enterprise

Voice Assistant

Voice input for Odoo forms with browser speech recognition or local Whisper transcription. Includes inline microphones, a floating assistant, and configurable provider settings.

Supports Char, Text, HTML, Many2one, Many2many Tags, Integer, Float, Date, and Datetime fields.

Built for daily backend use

Browser mode gives quick setup. Whisper mode gives better local control and accuracy. The architecture is also ready for future command actions and AI extensions.

Top Features

Key module capabilities at a glance.

01	Global Field Voice Support Voice support is injected centrally so supported fields can use inline microphones without custom widgets per model.

02	Floating Assistant Widget A floating assistant in the bottom-right corner supports transcript preview, provider switching, and manual insert actions.

03	Pluggable Provider Architecture Browser and Whisper providers are abstracted behind reusable services for future expansion and clean maintenance.

04	Structured Voice Parsing Spoken input is adapted for text, HTML, relation search, numeric values, dates, and datetimes.

05	Secure Whisper Uploads Audio uploads are authenticated, validated, and only used when local transcription is required.

06	Multi-Company Configuration Provider, language, fill mode, floating assistant, and debug settings can be configured per company.

Configuration

Recommended setup flow for production usage.

General Settings

Enable Voice Assistant
Select Browser or Whisper Local
Set the default language
Enable or disable continuous listening
Enable automatic field filling
Toggle the floating assistant widget
Enable debug mode for troubleshooting

Suggested Sequence

Install the module and refresh backend assets.
Open Settings > General Settings > Voice Assistant.
Select the provider based on your deployment model.
Test in Char or Text fields first.
Validate Whisper dependencies if local transcription is enabled.
Continue with HTML, Many2one, and Many2many Tags.

Whisper Setup

Install Whisper directly on the Odoo server when you want local transcription.

Recommended for production

Install using faster-whisper

Install the library inside the same Python environment where Odoo runs, then select Whisper Local in the module settings.

Install command

pip install faster-whisper

After installation

Restart Odoo, open the settings page, switch the provider to Whisper Local, and test with a short voice sample.

Alternative runtime

Using whisper.cpp

1	Install `whisper.cpp` on the server.
2	Keep the model file accessible on the machine.
3	Configure the command path in Odoo and use it when you prefer local binary execution.

Quick note

Browser mode needs no server speech library. Whisper mode needs local setup before users can transcribe audio.

Comparison: Browser & Whisper

Choose the provider that best fits your infrastructure, privacy expectations, and required accuracy.

Feature	Browser Provider Typical accuracy: 75% - 88%	Whisper Local Typical accuracy: 88% - 96%
Setup	No backend transcription setup required.	Requires `faster-whisper` or a configured `whisper.cpp` command.
Speed	Fast live transcript preview with minimal setup.	Slightly slower because audio is uploaded and processed on the server.
Privacy	Depends on browser engine and client-side speech services.	Better for private deployments with local server-side processing.
Best For	Quick rollout, lightweight deployment, and easy dictation.	Higher accuracy, local processing, and controlled infrastructure.
Trade-off	Easy to start, but results vary more by browser, microphone, and background noise.	Needs extra setup, but gives more consistent recognition quality.

Accuracy figures are indicative and vary based on microphone quality, speaker accent, browser engine, background noise, and Whisper model size.

Supported Voice Fields

The module supports practical backend fields where voice input makes sense.

Char Text HTML Editor Many2one Many2many Tags Integer Float Date Datetime

Screenshots

Preview the main screens used in setup and day-to-day dictation.

Step 1 - Voice Assistant Settings

This screenshot should show the main Voice Assistant settings where the administrator enables the feature and selects the provider.

Step 2 - Field-Level Microphone

This screenshot should highlight the inline microphone icon that appears on hover or focus inside a supported field.

Step 3 - Floating Voice Assistant

This screenshot should present the floating assistant panel with transcript preview, provider switcher, and fill mode controls.

Step 4 - Whisper Local Flow

This screenshot should show the Whisper-based transcription flow or a server-side setup example for local transcription.

30 Days Free Support Included

We provide 30 days of free support for bugs, issues, or technical questions related to the delivered module features.

Pysquad

Need Help?

Got questions or need help? Get in touch.

Email: solutions@pysquad.com

Phone: +91 8160395422

WhatsApp: +91 8160395422

Discover More

www.odoo.pysquad.com

Please log in to comment on this module

The author can leave a single reply to each comment.
This section is meant to ask simple questions or leave a rating. Every report of a problem experienced while using the module should be addressed to the author directly (refer to the following point).
If you want to start a discussion with the author or have a question related to your purchase, please use the support page.