Tag Archives: AI accessibility

RITS AI Voice Bridge v3.1

Posted on by
Reply

RITS AI Voice Bridge v3.1 is available now for both Windows and Mac.

RITS AI Voice Bridge v3.1 is a free, privacy-focused local utility from Reasonable IT Service that runs on your computer and adds a private voice layer to ChatGPT, Claude, DeepSeek, Gemini, and Grok in Google Chrome.

It supports local dictation, local readback, a floating Mic | Repeat | Stop control, voice command auto-send, selective re-reading of long AI responses, and a cleaner, more polished interface for Windows and macOS.

  • No cloud TTS
  • No API key
  • No extra account
  • No telemetry
  • No startup service
  • No platform-controlled voice mode required

Your AI writes. Your computer talks. You stay in control.

Note: Google Chrome and Python are required.

What’s New in v3.1

  • New support for Grok
  • Improved ChatGPT, Claude, DeepSeek, Gemini, and Grok handling
  • New Re-read from here… feature for long AI responses
  • New Repeat menu with Re-read entire response and Re-read from here…
  • Improved manual re-reading so page scrolling and DOM updates do not interrupt or restart selected playback
  • New built-in About panel with version information, product details, setup information, support links, and Reasonable IT Service attribution
  • Updated product branding throughout the application as RITS AI Voice Bridge
  • Updated default installation folder: RITS-AI-Voice-Bridge
  • Updated Chrome extension, Windows shortcut, Start Menu, and macOS launcher names
  • Improved installer cleanup and upgrade handling for existing installations

Core Features

  • Support for ChatGPT
  • Support for Claude
  • Support for DeepSeek
  • Support for Gemini
  • Support for Grok
  • Local dictation with Whisper
  • Read-aloud using your computer’s built-in system voice
  • Floating Mic | Repeat | Stop control
  • Full-response re-read
  • Re-read from here… for resuming long responses from a selected sentence
  • Stop control for interrupting local readback
  • Voice command auto-send
  • Windows and macOS keyboard shortcuts
  • Local voice processing architecture

What It Does

RITS AI Voice Bridge runs locally on your computer.

It adds a small floating control to supported AI chat sites in Chrome. You can dictate a prompt locally, insert it into the chat box, send it manually, or use a simple final phrase command to send it automatically.

When the AI responds, RITS AI Voice Bridge can read the response aloud using your computer’s local system voice.

If the response is long, you can replay the entire answer or use Re-read from here… to choose the sentence where read-aloud should resume.

RITS AI Voice Bridge does not replace ChatGPT, Claude, DeepSeek, Gemini, or Grok.

It adds a local voice layer on top of the normal text chat experience.

Re-read from Here

Long AI responses can be useful, but replaying an entire response just to hear one section again is not always practical.

In v3.1, clicking the Repeat button opens a compact menu with two options:

  • Re-read entire response
  • Re-read from here…

Choose Re-read from here…, then click the sentence where you want playback to resume.

RITS AI Voice Bridge starts from that point and continues through the remainder of the response.

This gives you much more control over long-form AI readback without changing the normal text chat experience.

Voice Command Auto-Send

RITS AI Voice Bridge supports a simple voice command for sending messages.

If your dictation ends with “send message” or “send a message”, the bridge removes that final command phrase and submits the remaining prompt automatically.

Example:

You say: Explain this in one paragraph send message

The AI site receives: Explain this in one paragraph

The command only triggers when the send phrase is the final phrase. Saying something like “send message to the client” will not trigger auto-send.

Dictation must still be ended using Enter, the Mic button, or the platform hotkey before the completed recording can be transcribed and the final send command detected.

Controls

RITS AI Voice Bridge keeps the controls simple.

  • Click the Mic button to start recording
  • The Mic button changes state while recording
  • Click the Mic button again to stop recording and transcribe
  • Press Enter while recording to stop and transcribe
  • Windows dictation hotkey: Ctrl + Shift + V
  • Mac dictation hotkey: Cmd + Shift + V
  • Click Repeat to choose how the latest AI response should be re-read
  • Choose Re-read entire response for full playback
  • Choose Re-read from here… to resume from a selected sentence
  • Click Stop to stop current local readback
  • Press Esc inside the AI site tab to stop local readback
  • Click the small ? button for About, version information, setup information, and support links

Why We Built It

Native voice modes can be convenient, but they come with tradeoffs.

The biggest one is control. With native voice features, your audio is handled through the platform’s voice system. That means the transcription process, retention rules, usage limits, available features, and overall voice experience are controlled by the platform.

For example, OpenAI’s own Voice Dictation FAQ says recorded dictation audio is sent to OpenAI’s models for transcription and retained for as long as the associated chat remains in your chat history.

OpenAI’s Voice documentation also explains that audio clips from Live and Advanced Voice conversations are retained for 30 days, while Standard Voice audio is deleted after transcription unless the user has chosen to share audio for model improvement.

That may be perfectly acceptable for many users, but we wanted another option.

With RITS AI Voice Bridge, dictation audio is sent only to the local server running on your own computer. The supported AI platform receives the final text prompt only when you choose to send it.

Voice features can also change over time. They can be limited, paywalled, removed, redesigned, or behave differently across platforms.

There is also a practical difference between using a platform’s native voice mode and using its normal text interface. RITS AI Voice Bridge lets you keep the regular chat experience while adding local voice functionality on top of it.

RITS AI Voice Bridge takes a simpler approach.

  • Use the normal AI chat in Chrome
  • Dictate locally on your own machine
  • Send only the final text prompt when you choose to send it
  • Let the AI answer normally in text
  • Let your own computer read the answer aloud locally
  • Replay the full response or resume from a selected point whenever you want

Less platform-controlled voice processing. More user control.

How It Works

RITS AI Voice Bridge runs a small local server on your computer at 127.0.0.1:5055.

The Chrome extension communicates with that local server.

When you dictate, your microphone audio is sent to the local server on your own machine, transcribed locally with Whisper, and inserted into the AI chat box as text.

When the AI responds, the bridge captures the response text and reads it aloud through your computer’s local system voice.

The supported AI platform receives what it normally receives: a text prompt.

Raw microphone audio is not sent to ChatGPT, Claude, DeepSeek, Gemini, or Grok by RITS AI Voice Bridge.

Why It Matters

RITS AI Voice Bridge gives you a local voice layer for the AI tools you already use.

You can continue using the normal ChatGPT, Claude, DeepSeek, Gemini, and Grok interfaces in Chrome while adding local dictation, local readback, and independent playback controls.

You keep the normal text conversation. You keep control over when your prompt is sent. Your computer handles the voice layer locally.

Native voice modes prioritize convenience. RITS AI Voice Bridge prioritizes local control, privacy, flexibility, and consistency.

Video Installation Guide ->

Please note – RITS AI Voice Bridge is not affiliated with, endorsed by, or sponsored by OpenAI, Anthropic, DeepSeek, Google, or xAI. ChatGPT, Claude, DeepSeek, Gemini, and Grok are trademarks of their respective owners.