ChatGPT Voice now connects spoken conversations to plugins, connected apps and longer tasks. OpenAI’s September 23 release notes confirm Live with plugins on web, iOS and Android, and Voice in Work on web and mobile. In the ChatGPT desktop app, Voice also works with Work and Codex, where you can start tasks, check progress and steer work. The experience and available tools depend on your plan, device, client and workspace. GPT-6 Astra can help with harder search and reasoning in Voice; GPT-6 Sol and Luna are available in Work and Codex, subject to rollout and access. Read OpenAI’s announcement and watch its demo.
For a tool-assisted session, open Work, add the relevant file or connect the service, then choose Voice and describe the result you need. In the desktop app, Voice also works in Chat and Codex. You can keep talking to refine an active task or ask Voice to start and coordinate separate work.
Rollout note: The web screenshots show one account on September 23; mobile screens were not captured. OpenAI’s September 23 release notes confirm Live plugins on web, iOS and Android and Voice in Work on web and mobile. The dedicated product pages describe the desktop app’s Work and Codex task controls. Codex itself is not selectable on web or mobile; the ChatGPT mobile app can reach supported desktop Codex chats through Remote. Feature and tool availability still depends on your plan, app version and workspace settings.
Start your first useful Voice session
Begin with a small request that has an obvious result. A short, sourced briefing is a better first test than handing over your entire working day.
- Open ChatGPT in a desktop browser, or update the ChatGPT app and sign in.
- Select Work for a task that needs tools or a finished file. Choose a model available to your account; the default is a reasonable starting point.
- Add the relevant file or connect a plugin if the task needs private information. Public web research does not require connecting your inbox.
- Choose the Voice control. In the web screenshots, this is the blue button with vertical sound bars on the right of the composer. The adjacent microphone is dictation.
- Allow microphone access when prompted and complete any voice setup shown. Start speaking.
- Review the written result, sources and tool activity. Use the stop or end-call control when you finish.
Try this first:
“Search OpenAI’s official sources for the latest ChatGPT Voice changes. Explain the three most useful changes in under a minute, then leave a short written summary with links. Tell me which features are still rolling out.”
If it produces an answer without sources, follow up: “Please search now and show me the pages you used.” The evidence of a search is the search activity and linked results, not a confident spoken answer. OpenAI documents how search activity and citations appear in chat.
Voice, dictation, Chat and Work: choose the right control
| What you want | Choose | What to expect |
|---|---|---|
| Speak a prompt, edit it, then submit it | Dictation | Your speech becomes text in the composer. |
| Have a back-and-forth spoken conversation | Voice in Chat (Live) | Ask follow-ups, interrupt, and use available plugins or connected apps. |
| Use sources and tools to produce a result | Voice in Work | Describe the job, steer it while it runs, and inspect the output. |
| Discuss a software task and its progress | Voice in Codex in the desktop app | Use task context, ask for progress, or change direction; existing-task voice is rolling out. |
| Coordinate longer work | Voice in Work or Codex on desktop | Start a separate task, check blockers, and give follow-up instructions. |
Choose Live, Advanced or Standard
In ChatGPT Settings → Voice, choose the mode available to your account. Live is the real-time mode that can use web search, memory, plugins or connected apps, and text or images in the conversation. Live does not support video or screen sharing. On supported mobile accounts, Advanced retains video and screen-sharing controls. Standard transcribes your speech before ChatGPT responds. Modes and controls vary by plan, workspace, region, app version and account. Live accepts text and images and may accept manually attached supported files, but it cannot browse or add files from ChatGPT Library. For accurate limits and account-specific options, check OpenAI’s current Voice setup and availability notes.
OpenAI’s Work guide recommends Work for assignments with multiple steps, sources or tools and an output you will review. That makes it the useful starting point for this tutorial. Installing a plugin and switching to Work are separate steps; neither grants access to an external account by itself.
How to use ChatGPT Voice on each device
On the web
In ChatGPT, select Chat or Work at the top of a new conversation. In the Work interface we inspected, the composer includes the model selector, dictation microphone and Start Voice button. Project, Files and Plugins controls sit below it. Use the plus menu to add material before you start.
You can prepare context with your keyboard and then continue by voice. For example, attach a report, select the relevant plugin, and say: “Use the report I attached and explain the unresolved questions.” Voice is especially useful for clarifying the assignment and discussing the result.
On iPhone or Android
For a spoken Chat conversation, open the ChatGPT app, select the Voice icon in the message bar, allow microphone access if prompted, and choose a voice on first use. For a tool-assisted Work session, select Work, then select its Voice control. Work Voice can use connected apps, create documents, presentations and spreadsheets, or use a browser. If a task is still running when you end the call, it can continue in text. Both Voice and Work access are required; availability depends on plan and workspace. For video or screen sharing on a supported mobile account, choose Advanced rather than Live. In Settings → Voice, you can also enable Background conversations to keep a session going in other apps or while the phone is locked, or Start with Voice on supported app versions. ChatGPT also works with CarPlay on supported iPhones; set it up before driving and do not interact with the device while the car is moving. Check current mobile controls and availability.
On mobile, a Codex task is a different route: Codex is not a selectable web or mobile experience, though supported desktop Codex chats can be reached in the ChatGPT app’s Remote tab. Plugins marked Desktop only still require the desktop app. This guide’s screenshots are from the web, not a mobile capture.
Keep names, dates and destinations visible when an action matters. It is easier to catch the wrong recipient in a written draft than in a spoken recap.
In the desktop app
Voice works in Chat, Work and Codex. Open a chat or task and choose Start voice chat, or select Start new voice chat to begin. On first use, allow microphone access, choose a voice, and review screen context on macOS if you plan to use it. You can interrupt, ask for progress, change direction, start a separate task, or send a follow-up instruction. A shortcut is available under Settings → Voice → Voice chat hotkey. Only one desktop voice chat can be active at a time. OpenAI’s Voice instructions cover setup and task coordination.
On macOS, Screen context can send an image and accessible text from the frontmost window, including text outside the visible scroll area. The app may request Screen & System Audio Recording and Accessibility permissions. Close sensitive windows before using it; an organization can disable this feature. For tool actions on web or mobile that need approval, review and approve or decline on screen; Voice does not accept spoken approval.
For work that needs a local file or desktop app, check where the task is running. Desktop Work can offer local and cloud execution. A cloud task does not automatically inherit the files or apps on your computer. OpenAI explains the local/cloud choice here.
How Voice uses tools and plugins
A tool lets ChatGPT retrieve information or perform a supported action. A plugin supplies access to a particular service or workflow. For example, a calendar plugin can make calendar information available; a file tool can help create a spreadsheet. Each capability still needs the right account access and permissions.
During a Live conversation, ask ChatGPT to use a plugin or connected app available to your account. OpenAI names email, calendar and Slack plugins, plus document, presentation, spreadsheet and browser workflows in Work. A specific action still needs the relevant connection and permission. On web and mobile, review approval requests on screen: spoken approval is not supported.
| Job | Useful access | Result to inspect |
|---|---|---|
| Find current public information | Web search | Source links and dates |
| Summarize messages or meetings | Connected email, Slack or calendar plugin | Correct account, time range and source items |
| Analyze your material | Uploaded files or a connected file service | Correct document version and supported conclusions |
| Create a deliverable | Available document, spreadsheet, presentation or site tools | A usable file or preview, with working content |
| Work through a website | Supported browser tools and any required sign-in | The destination, proposed changes and final page state |
Connect a plugin once, then name it in your request
- Open Plugins. On the web interface shown here, the composer’s Plugins menu also offers Connect plugins and Browse all plugins.
- Find the service you need and open its details. Check the developer, supported capabilities and any platform restrictions.
- Select Install plugin or the plus/install control shown by your interface.
- Complete the service’s connection flow if required. Confirm the account or workspace and review the requested access.
- Start a new chat after installation where required by the plugin instructions, then choose Chat or Work and start a Live Voice session.
- Name the service and scope aloud: “Use Slack to summarize the last seven days in the launch channel.” In a typed prompt, you can use @ to select a plugin explicitly.
For connection errors, test one small request first. “Can you find the event named Product Review on my work calendar tomorrow?” is easier to diagnose than “Organize my week.” If nothing appears, verify the connected account and access before broadening the request. OpenAI’s installation instructions explain when a new chat or additional authentication is needed.
A complete example: prepare for tomorrow’s meetings
Once your calendar and email plugins are connected, try the sequence below. These are suggested prompts and review steps; this guide does not claim to have run them against a private inbox.
1. Define the sources, time window and output.
“Use my work calendar to find tomorrow’s meetings in Pacific Time. For each meeting, search my connected work email for the relevant recent thread. Make a one-page briefing with the purpose, open questions and anything I promised to deliver. Include links to the sources. Read me the three things I should prepare first. Do not send messages or change events.”
2. Correct the scope while it works.
“Focus on the customer review at 2 p.m. Use only material from the last two weeks. Separate confirmed commitments from your suggestions.”
3. Check whether the evidence supports the briefing.
“Which items came directly from the calendar or email, and which are your interpretation? Show me the source for the proposed deadline.”
4. Review a draft before using a write action.
“Draft a reply asking for the missing agenda. Show me the recipient, subject and full message before sending.”
The workflow is complete when you have the briefing, can open its supporting sources, and have resolved anything marked uncertain. If you decide to send the reply, approve the exact recipient and wording. A spoken description of a draft is not a substitute for checking the draft itself.
Six practical Voice prompts to try
Use the same pattern each time: source + task + constraints + output + review point. Replace the bracketed details before speaking. The examples depend on the tools and permissions available in your conversation.
1. Get a useful Slack catch-up
“Use Slack to review [channel] since Monday morning. Tell me the decisions, unresolved blockers and requests addressed to me. Link to each relevant message. Keep the spoken briefing under two minutes and put the full list in the chat.”
Ask it to distinguish a proposal from an agreed decision. A conversation about doing something does not establish that it happened.
2. Build a comparison spreadsheet
“Use these three supplier quotes. Create a spreadsheet with price, currency, delivery time, included services and renewal terms. Leave missing details blank and flag them. Explain the two biggest differences out loud. Show the formulas behind any totals.”
Check currency, tax treatment, units and formulas before relying on the result. Specify sheet names and cell references when requesting revisions.
3. Turn notes into a presentation
“Turn the attached notes into six slides for a ten-minute team briefing. Use one main point per slide, add speaker notes and cite the source for factual claims. Talk me through the proposed outline before building the deck.”
Review the exported slides as well as the outline. A good spoken structure can still produce crowded slides or unsupported claims.
4. Research and prepare a short document
“Research [topic] using current primary sources. Create a two-page briefing with the main options, evidence, uncertainties and source links. Give me a sixty-second spoken overview, then ask which option I want to explore.”
Set a date range when recency matters. Ask for explicit gaps instead of inviting it to fill missing information with guesses.
5. Work through a website
“Use the browser to compare the public plans on these three websites. Record the monthly price, usage limits and cancellation terms with links. Stop before signing up, starting a trial or entering payment details.”
Provide the websites and the exact information you need. Check the browser’s result and the source pages before taking the next step.
6. Build a draft site from a spoken brief
“Create a draft one-page website for [project]. Use the attached copy and logo. Include the offer, three features, a short FAQ and a contact section. Ask me about missing details, then show me the preview before publishing.”
Review the page on a phone-sized screen, test its links, and check the contact destination. Creating a preview and publishing it are separate outcomes; say which one you want.
Which model should you choose for Voice?
The model depends on the Voice experience. OpenAI says Voice can use GPT-5.6 or GPT-6 Astra for harder questions that need search or reasoning, using the model and effort controls available in Chat. GPT-6 Sol and Luna are Work and Codex models, alongside Astra where available. The screenshot below shows the Work model menu on one account; it does not show which audio model handles a Live conversation.
| Model | A sensible starting use | Practical advice |
|---|---|---|
| GPT-6 Luna | A clear summary, extraction or repeatable task | Keep the scope specific and check the result. |
| GPT-6 Sol | Everyday work involving several steps or tools | A reasonable starting choice for briefings and document workflows. |
| GPT-6 Astra | A demanding assignment requiring deeper reasoning and judgment | Use it when the task’s difficulty warrants more computation. |
These are task-selection recommendations based on OpenAI’s model guidance, not results from a Voice benchmark. GPT-6 Sol and Luna appear in Work and Codex rather than regular Chat, and model or effort options vary by plan and workspace. Voice is the interface; the tools and models available to it come from the selected experience.
Check your Live Voice allowance
For Voice in Chat, OpenAI measures Live use over a rolling 24-hour period and shows a notice when you reach a limit. Its current Help Center lists these consumer allowances; Free access can change:
| Plan | Current Live Voice allowance in Chat |
|---|---|
| Free | Limited access to GPT-Live-1 mini; limits may change. |
| Go | Up to 3 hours with GPT-Live-1 mini. |
| Plus | Up to 3 hours with GPT-Live-1. |
| Pro ($100/month) | Up to 15 hours with GPT-Live-1. |
| Pro ($200/month) | Unlimited GPT-Live-1. |
These are Chat limits, not a universal allowance: business and education billing differs. Voice in Work follows the plan’s Voice allowance and its tasks also count toward normal Work usage; desktop Voice has separate pricing and limits. Work and Codex usage also depends on task, model, reasoning and tools. Check your live usage display and OpenAI’s current Voice limits or plan information before planning a long session. Developer API prices are a separate billing context.
Give Voice the right context and permissions
Start with the smallest source set that can answer the question. One document, a named channel and a date range usually give you a result that is easier to verify than unrestricted instructions to search everything.
On macOS, the desktop app’s Settings → Voice → Screen context can let ChatGPT inspect the frontmost window when you ask it to take a look. OpenAI warns that the resulting appshot can include accessible text outside the visible scroll area. Close sensitive windows or supply a specific file instead when that is more appropriate. Organizations can disable this capability. See the screen-context instructions.
Screen context and permission to operate an app are different. Showing a window provides context; actions still depend on available tools and permissions.
For connected services, read the access requested during setup. A read-capable integration and a write-capable integration have different consequences. OpenAI says the external service’s terms and privacy policy apply when data is sent through its connection. Uninstalling a plugin may also leave a separately connected integration in place, so review those connections if you want to revoke access. Read the plugin permissions guidance.
OpenAI says Live and Advanced audio clips are retained with their transcripts for 30 days; deleting a chat removes them within that period, subject to limited exceptions. Standard-mode audio is deleted after transcription unless you choose to share it. Depending on your plan and settings, transcripts may be used to improve models when Improve the model for everyone is on; audio and video clips are used for training only if you opt in to share them. Review Settings → Data Controls and your organization’s policy before a sensitive conversation. OpenAI’s Voice data controls and retention details explain the distinctions.
For any send, edit or publication, give an explicit destination and review point. “Draft a reply for review” and “Send this exact reply to this person” are different instructions. Voice should make those instructions easier to give, not less precise.
Troubleshooting: what to check first
| Problem | First check | Next step |
|---|---|---|
| You speak, but only text appears | You may have chosen dictation. | Select Start Voice, the separate sound-bars control. |
| Voice is missing in Work | App version, selected surface and rollout access. | Update the app or reload the web page. Check your plan and workspace restrictions. |
| Voice cannot hear you | Microphone permission and selected input device. | Check browser/app and operating-system microphone settings; test the microphone in another app. |
| A plugin appears but cannot read your data | Installation, authentication and the connected account. | Complete the connection, start a new chat, then test one named item. |
| A plugin works on desktop but not mobile | Its platform requirements. | Check for a Desktop only label and use the supported surface. |
| Astra, Sol or Luna is missing | Whether you are in Work or Codex, plus plan and workspace access. | Use an available model while the rollout reaches your account. |
| The answer sounds current but has no evidence | Whether a search or retrieval tool ran. | Ask it to search explicitly and supply the source links. |
| The transcript misses or changes words | OpenAI says Voice transcripts are not verbatim; noise or overlap can affect recognition. | Reduce background noise, restate names and numbers, and check the written response. Use dictation and edit the text first when exact wording matters. |
| It gives you the wrong event or person | Ambiguous name, date, time zone or account. | Spell the name, specify the full date and time zone, and inspect the written result. |
| Desktop Voice will not start in another window | An existing voice conversation may already be active. | End the other Voice session first. OpenAI documents one active Voice conversation at a time. |
| The task is slow or hits a limit | Scope, model, effort and available usage. | Ask for a smaller output, reduce unnecessary context, or try a lighter model. |
OpenAI’s Voice troubleshooting page and usage guide are the references for account and limit questions. If a feature described here is missing, verify the client version, plan and workspace rollout before changing your prompt.
Frequently asked questions
Can ChatGPT Voice use tools now?
Yes. Live supports the plugins and connected apps available to your account on web, iOS and Android. Voice in Work on web and mobile can use connected apps and browser tools. In the desktop app, Voice in Work and Codex can start tasks, check progress and coordinate follow-up work. Existing service connections, permissions and workspace controls still apply.
Do I need a paid plan?
Not for every Voice feature. OpenAI says Free and Go users can use Voice in Chat with the plugins their plan supports. Voice in Work requires both Voice and Work access; Work on web and mobile is limited to eligible plans and managed workspaces. Limits and availability differ between Chat, Work and desktop Voice, so check the Voice limits and Work and Codex availability for your account.
Do I need an API key or to write code?
The ChatGPT interface workflow in this guide uses your ChatGPT account and normal plugin connections. It does not require you to build a voice application or supply a developer API key.
Can I interrupt it or change the assignment?
Yes. OpenAI documents natural turn-taking and interruption. Give a concrete correction: “Use the revised file,” “Limit this to the last seven days,” or “Pause before sending anything.” Check that the revised instruction appears in the task and affects the result.
Can I use files and projects while talking?
OpenAI’s August 3–7 update added uploaded-file and ChatGPT Project support to Voice. Live still cannot browse or add items directly from ChatGPT Library; attach a supported file manually if your account allows it, then name the material in your request and confirm its version.
Does stopping Voice stop the work it started?
No. OpenAI says an unfinished Work task can continue in text after you end a Voice call. Desktop Voice can also start and coordinate separate tasks. If you want work to stop, say so explicitly and check the task’s status; if you only want to stop talking, end the call and inspect the written result later.
Sources, verification and updates
This guide combines OpenAI’s announcement, current Help Center and product documentation, and six screenshots captured from ChatGPT’s web interface on September 23, 2026. We verified the displayed web Voice entry points, model menu, file controls and plugin setup screens. Mobile controls, spoken tool execution, microphone quality and latency were not independently tested for this edition. The sample prompts are suggested workflows, not test results.
The updated OpenAI Help Center distinguishes Live Voice in Chat on web and mobile, Voice in Work on web and mobile, and Voice in Work or Codex in the desktop app. An older dedicated Learn page focuses on desktop setup and paired iOS Remote access for supported desktop tasks; the current Help Center clarifies the separate mobile Work flow. Codex remains unavailable as a selectable mobile or web experience. We keep the account-specific screenshots separate from the broader platform and plan availability claims, and do not infer an undocumented audio architecture from model names.
- OpenAI’s September 23 Voice announcement and demo
- ChatGPT Voice: setup, task coordination, screen context and troubleshooting
- Remote connections for supported desktop tasks
- ChatGPT Voice: platforms, Live plugins, permissions and limits
- ChatGPT Work and Codex: platforms, Voice and permissions
- ChatGPT release notes, including September 23 Voice changes
- What’s new: current ChatGPT and Codex updates
- ChatGPT and Codex changelog
- Get started with ChatGPT Work
- Plugins: installation, platform support and permissions
- Models: Astra, Sol, Luna and selection controls
- Pricing, shared usage and feature availability
- Web search and source visibility
- Voice file and Project support
Related Kingy guides: GPT-6 Sol and Luna specs and pricing, ChatGPT Work and editable files, and choosing the right ChatGPT workflow.
| Date | Editorial update |
|---|---|
| September 26, 2026 | No new Voice rollout appeared in the release notes after September 23; September 25 notes cover account security. OpenAI’s Voice Help Center was refreshed and now specifies plan-based GPT-Live usage limits, model controls for harder questions, Live’s file/Library boundary, and mobile background, auto-start and CarPlay options. Added the current consumer Chat limits with a date-sensitive caveat, clarified file attachment versus Library access, and added practical mobile controls. Screenshots remain unchanged because no altered captured web control was confirmed; mobile behavior is based on official documentation, not hands-on testing. |
| September 25, 2026 | No new dated Voice rollout appeared in OpenAI’s release notes after September 23. The refreshed Voice Help Center adds practical distinctions among Live, Advanced and Standard, the mobile video/screen-sharing limitation in Live, data retention and training controls, and the warning that transcripts are not verbatim. Added these setup, privacy and troubleshooting details. Existing web screenshots remain accurate; no mobile UI capture or hands-on mobile test is claimed. |
| September 24, 2026 | Updated for OpenAI’s September 23 Help Center notes: Live plugins on web and mobile, Voice in Work on web and mobile, desktop Work and Codex voice task controls, on-screen approvals, and different plan and usage rules by experience. Clarified that GPT-6 Sol and Luna apply to Work and Codex, while Voice may use GPT-6 Astra for harder Chat questions. No new screenshots were needed; the guide’s mobile workflows are sourced from current OpenAI instructions and are not presented as captured tests. |
| September 23, 2026 | Published the rollout guide with six web screenshots, tool setup, practical prompts, model selection, permissions and troubleshooting. Daily rollout checks are scheduled for September 24, 25 and 26; verified changes will be added here. |
For your first session, pick one source and one output: summarize one document, explain one calendar event, or prepare one sourced briefing. Inspect that result before expanding the job.