> For the complete documentation index, see [llms.txt](https://passion-io.gitbook.io/help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://passion-io.gitbook.io/help/make-your-ai-sound-like-you/add-a-voice-sample.md).

# Add a Voice Sample

Give your AI a spoken voice that sounds like you by recording or uploading a sample.

> **Your AI** is available on certain plans and app types. If you don't see the AI block in your sidebar, please check our pricing page for more information.

![Your AI’s voice](https://2428968841-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FTPk2caKn6lTiyi0ejFkg%2Fuploads%2Fgit-blob-b1986546bc33b3c6a181142456d9106db3758070%2Fadd-resources.png?alt=media)

## In This Article

* [Record a Sample](#record-a-sample)
* [Upload a Sample](#upload-a-sample)
* [Check the Status and Preview](#check-the-status-and-preview)

A voice sample lets your AI speak in chat with your warmth and pacing. They'll sound directionally like you — same tone, not an exact replica. Record in the browser or upload a file.

## Record a Sample

Recording takes under a minute and works straight from the browser.

1. In the sidebar, open the AI block — it carries your AI's name — and select **Identity & voice** (previously Profile).
2. In **Voice samples**, select **Record sample** and allow microphone access.
3. Read naturally for 30–60 seconds (10 seconds minimum, 270 seconds maximum). Read at your normal pace in a quiet room, one mic, no music.
4. Select **Stop** when you're done.
5. Play back the preview, then select **Keep** to save it or **Discard** to try again.

## Upload a Sample

Already have a recording? Upload it instead.

1. In **Voice samples**, select **Upload file**.
2. Choose an **MP3** or **WAV** recording from your device.

## Check the Status and Preview

Each sample shows where it stands and previews how clients will hear your AI.

1. Watch the sample status: **Waiting**, **Verified**, or **Retry**.
2. Once at least one sample is verified, your AI builds a voice model and the page shows **Current voice** — a short preview of how clients will hear them.
3. Select the play button there to listen.

Removing your only sample also removes the voice model, so your AI falls back to a generic voice until you add another.

## Related

* [Set Your AI's Speaking Pace](/help/make-your-ai-sound-like-you/set-voice-speed.md)
* [How Your AI Sounds Like You](/help/make-your-ai-sound-like-you/how-your-ai-sounds-like-you.md)

For more assistance, please contact us.