# Voice conversations

Talk with your Opser agent, choose a voice, and understand live voice credits.

Source: https://docs.opser.com/agents/voice/

## Talk with your agent
In an empty chat input, choose the voice waveform button to start a live conversation. When you type or attach a file, that position becomes Send. The separate microphone button dictates an editable text draft instead.

Allow microphone access when your browser asks. On first use, review the credit rate and choose **Start with credits**. You can ask about your CRM, deals, tasks, or other apps the selected agent can access. Results and approval cards appear in the same chat.

Your words and the spoken reply appear progressively as messages in the chat. The compact card above the input has an Opser mark that responds to your microphone and the agent’s audio, plus a mute control. It respects reduced-motion preferences. The voice button becomes an **X** to end the conversation. Pricing appears before your first call and in Voice settings, keeping the call controls focused on the conversation.

Within each voice reply, tool activity and detailed agent results appear before the spoken transcript. Files, approvals, errors, and results that arrive after you end voice remain available. The transcript stays in the chat after the call settles.

## Control your conversation
Use the microphone control to mute yourself and **End voice** to stop the call. Muting does not stop credit usage. Interrupting spoken audio does not cancel an action already running: use the chat’s Stop control when you want to cancel agent work. Ending voice leaves authorized work in chat.

Voice stays connected while you navigate within Opser. On desktop, a working conversation follows you into the agent sidebar; on mobile, compact controls let you mute or end voice while viewing an app. Idle conversations do not open automatically. Closing the tab, signing out, losing the connection, reaching your time limit, or running out of credits ends the call. Reconnecting requires a new call; actions are not replayed automatically.

## Keyboard shortcuts
Focus the chat and use **Ctrl+Shift+M** to start or stop dictation, or **Ctrl+Shift+Space** to start or end live voice. On Mac, use **Cmd** instead of Ctrl. The shortcuts appear in each button’s tooltip and follow the same controls: voice starts when the input is empty, the first-use credit notice still appears, and disabled controls stay disabled. If two chat panels are open, focus the one you want to use. Dictation creates an editable draft; it does not send the message.

## Choose your voice
GPT Live speaks with your selected Opser agent's name and personality. Voice tool work uses GPT-5.6 Luna with low reasoning, with the full toolbox and dynamic app tools available. Text chat keeps its configured model and reasoning. If your agent uses a connected Codex subscription, voice tool work uses Luna through that subscription; otherwise it uses the metered OpenAI API. Live audio is always billed separately in credits.

Open **Settings → Voice** to choose the agent’s voice, turn captions on or off, and set a maximum call length of 5, 10, or 15 minutes. Play the preview beside any voice to hear a short sample without spending workspace credits. Changes apply to your next call.

## Understand credits
The first-use notice and **Settings → Voice** show your workspace’s current credit rate. Live voice is billed per second, with a 15-second minimum when connecting. Silence, muted time, and waiting for the agent count while the session is open.

Opser reserves a short amount of credit ahead of use. Unused reserved credits are returned when the call is settled. If a connection fails before final usage arrives, Opser retains the confirmed usage it received and marks the final amount as unconfirmed for billing review.

The agent’s model and tools are charged separately at their usual rates. Live voice and dictation use workspace credits even when your agent’s text model uses your connected ChatGPT subscription. Dictation uses the recording’s duration; Voice settings show its separate rate.

Open **Settings → Usage** to see voice and dictation alongside other model usage and inspect the credit ledger for reservations and refunds. See [Credits and usage](https://docs.opser.com/billing/usage/).

## Audio and access
OpenAI processes the audio. Opser retains text transcripts, not audio recordings. Voice uses the selected agent’s existing access and approval policies. Review approval cards in chat before allowing actions that need your approval.

If voice cannot connect, check browser microphone permission and your workspace’s credit balance. Use a browser with WebRTC support; voice availability in an embedded mobile browser depends on its microphone support.