# Your first conversion

A recording in, the same recording in another voice out. What Voice Changer actually does, why the target list is shorter than the voice catalogue, and what the three settings are for.

Canonical URL: https://audiopod.ai/guides/voicechanger/your-first-conversion
Last updated: 2026-08-17

## About this lesson

- Track: [Voice Changer](https://audiopod.ai/guides/voicechanger)
- Lesson 1 · start · 5 min read

## Steps

1. Bring in a short, clean recording — Thirty seconds of one person talking, recorded close, with nothing much behind them. One file at a time, dragged in or picked from your machine. There is no recorder on this tab and no way to paste a link, so a phone memo or a call recording has to be a file before it can be converted. Start short: you are billed by the length of what you put in, so a first attempt should be cheap.
2. Pick a target voice — Not every voice you can speak text with can be a conversion target. Conversion needs a stored reference recording of the target, so the picker offers only finished voices that have one — your own cloned voices, and catalogue voices held as real recordings. Voices that exist as a preview rather than a stored clip are perfectly good for reading text and cannot be converted toward, so the list here is shorter than the catalogue and that is not a fault. Choose one near your own range for a first run — a target far from your voice is the harder case and a bad thing to learn on.
3. Leave the three settings where they are — Conversion Settings holds Preserve Timing, Quality and Pitch Shift, and the defaults are the sensible first run. In particular, leave Pitch Shift at 0 — it is the control that looks like an effect and is not one.
4. Check the estimate, then run it — The credit figure appears once the file is loaded. 990 credits per minute of source audio, whatever you set the controls to. Then press Change Voice.
5. Play the result against your source — The step people skip and the only one that tells you anything. Listen to the same twenty seconds of both. Are the words all there? Is the timing still yours? And does it sound like a person, or like a voice being operated?

## Lesson

Voice conversion keeps the performance and replaces the voice. Your words, your timing, your emphasis and your pauses all survive; what changes is who appears to be saying them. It is not an effects box and it does not rewrite what was said — one recording goes in, the same recording in a different voice comes back.

> **Warning:** There are no effects. No robot, no alien, no monster, no preset rack, and nothing that runs live on your microphone — despite what you may have read on our own feature page, which is wrong and is being fixed. There are three settings on this tab and one of them is a pitch slider.

> **Note:** There is no plan gate on this tool. Every account can run it, including a free one — the only limit is credits. Worth saying plainly, because much of the studio is not like that and readers assume a lock that is not there.

### Bring in your Source Audio

One file at a time, dragged in or picked from your machine. There is no recorder on this tab and no way to paste a link, so a phone memo or a call recording has to be a file before it can be converted. Video is accepted as well as audio — WAV, MP3, FLAC, OGG, OPUS, AAC, M4A, WEBM, MP4, MOV, AVI, WMV, MPG, MPEG, 3GP and MKV — and either way what comes back is a single audio file. How large and how long a source file may be depends on your plan, and the uploader enforces your account's real figures whatever the line under the dropzone says. That line is fixed text on this particular tab rather than your plan's ceiling, so treat a rejected upload as the authority and not the label.

> **Tip:** Start with thirty seconds, not with the whole project. You are billed on the length of the source, so the cost of finding out whether a target suits your voice is entirely under your control — 495 credits for a half-minute test against 29,700 for a half-hour episode.

### Pick a Target Voice

Not every voice you can speak text with can be a conversion target. Conversion needs a stored reference recording of the target, so the picker offers only finished voices that have one — your own cloned voices, and catalogue voices held as real recordings. Voices that exist as a preview rather than a stored clip are perfectly good for reading text and cannot be converted toward, so the list here is shorter than the catalogue and that is not a fault.

If nothing in the list is the voice you want, the answer is to create one: a cloned voice is a conversion target the moment it finishes. Cloning belongs to the Voice Studio track and is taught there rather than repeated here.

> **Tip:** Cloning, directing a voice and reading typed text all live in the Voice Studio track at /guides/voice. This track starts where you already have a recording.

### The three settings

Conversion Settings is the whole of the control surface: Preserve Timing, Quality and Pitch Shift. The next lesson is about when to touch them; on a first run, do not.

*Conversion Settings, with the tool's own ranges.*

| Setting | What it does |
| --- | --- |
| Preserve Timing — On or off. On by default. | Holds your source recording's rhythm — where the pauses fall, how long each word takes — instead of letting the target voice re-time the line. Leave it on. It is what keeps a converted take in sync with video, and turning it off is a choice you should make deliberately rather than while exploring. |
| Quality — Standard, High. Starts on High. | Trades processing time against result. It is not a strength dial and it does not change what you are billed — the credit figure is the length of your source and nothing else, so there is no cheaper setting to fall back to. |
| Pitch Shift — -12 to +12 semitones, in whole steps of 1. Default 0. | Transposes the result up or down after conversion. It is a transposition, not a re-performance: every note moves by the same amount, so a large shift makes the voice sound processed rather than making it sound like a different person. This is the control most likely to be misused, because it is the one that looks like an effect. |

> **Note:** The file type of the result — MP3, WAV or OGG, MP3 unless you change it — is set by the Format menu on the Text to Speech settings pane, not on this tab. It applies to conversions all the same. If you need a WAV, switch tabs, change Format, switch back, then run.

### What it costs

990 credits per minute of source audio, whatever you set the controls to — 990 credits for a minute, 9,900 for ten, 59,400 for an hour. Nothing you set changes that figure, which makes the arithmetic pleasantly simple and makes a failed conversion cost exactly as much as a good one.

> **Warning:** The credit figure appears once the file is loaded, and your browser works it out from the length of the audio rather than asking the server. If it cannot read the length — an unusual container, a video whose audio track it will not decode — the estimate shows nothing and the job still runs at the same rate. That is the one case where you find out the cost afterwards.

### What comes back

*The output of a finished job.*

| What | Detail |
| --- | --- |
| One converted audio file | The same recording in the target voice, with its own player and a download button. Your source is untouched and nothing is split apart — one file in, one file out. A video source comes back as audio only; the picture is not carried through. |
| A row in the shared history | Labelled with the target voice and your original filename, so a batch of takes is still tellable apart a week later. The history on this tab shows conversions only — your typed-text generations are filtered out of it. |
| A handoff to the Studio | Every completed job carries an "function(){throw Error("Attempted to call OPEN_IN_STUDIO_LABEL() from the server but OPEN_IN_STUDIO_LABEL is on the client. It's not possible to invoke a client function from the server, it can only be rendered as a Component or passed to props of a Client Component.")}" button, which takes the converted audio straight into the editor instead of making you download and re-upload it. That is where levelling, trimming and laying it against picture happen. |

Conversions collect in the History tab, newest first, each with its player and its download. The delete control there appears on jobs that did not finish; a completed conversion stays in your history.

### Check that it worked

1. **Play twenty seconds of your source** — Not from memory. You need the two close together in your ears, because what you are judging is a difference and it is easy to talk yourself into one.
2. **Play the same twenty seconds of the result** — Check the obvious things first: every word present, nothing clipped off the front, the timing still yours. That part is usually right and quick to confirm.
3. **Now ask whether it sounds like a person** — Not whether it sounds like the target — whether it sounds like anybody at all. A conversion can be perfectly intelligible and still land in the uncanny middle, and that is the failure this tool actually has. Nothing on screen will mention it: the job says it succeeded either way.

If it held up, you are done: download it, or use function(){throw Error("Attempted to call OPEN_IN_STUDIO_LABEL() from the server but OPEN_IN_STUDIO_LABEL is on the client. It's not possible to invoke a client function from the server, it can only be rendered as a Component or passed to props of a Client Component.")} to take it straight into the editor. If it came back wobbly, smeared or oddly not-anyone, that is not a mistake you made with the settings — it is almost always something about the recording you put in, and the next lesson is about which something.

## FAQ

**Do I need a paid plan for this?**
No. Voice Changer has no plan gate at all — a free account can run it, and the only things you need are credits and a target voice with a stored recording behind it. How large and how long a single source file may be does depend on your plan.

**What does it cost?**
990 credits per minute of source audio, whatever you set the controls to. A one-minute take is about 990 credits, ten minutes about 9,900 and an hour about 59,400. The target voice, the quality setting and the pitch make no difference to the price — you pay for the length of your source and nothing else.

**Why can't I pick most of the voices?**
Not every voice you can speak text with can be a conversion target. Conversion needs a stored reference recording of the target, so the picker offers only finished voices that have one — your own cloned voices, and catalogue voices held as real recordings. Voices that exist as a preview rather than a stored clip are perfectly good for reading text and cannot be converted toward, so the list here is shorter than the catalogue and that is not a fault. If nothing in the list is the voice you want, the answer is to create one: a cloned voice is a conversion target the moment it finishes. Cloning belongs to the Voice Studio track and is taught there rather than repeated here.

**Can I record straight into it, or paste a link?**
No. One file at a time, dragged in or picked from your machine. There is no recorder on this tab and no way to paste a link, so a phone memo or a call recording has to be a file before it can be converted. It does accept video as well as audio, so a screen recording or a camera file can go in directly — the result comes back as audio only.

**What files can I upload?**
Audio and video both: WAV, MP3, FLAC, OGG, OPUS, AAC, M4A, WEBM, MP4, MOV, AVI, WMV, MPG, MPEG, 3GP and MKV. How large and how long a source file may be depends on your plan, and the uploader enforces your account's real figures whatever the line under the dropzone says. That line is fixed text on this particular tab rather than your plan's ceiling, so treat a rejected upload as the authority and not the label.

**Where do I choose WAV instead of MP3?**
The file type of the result — MP3, WAV or OGG, MP3 unless you change it — is set by the Format menu on the Text to Speech settings pane, not on this tab. It applies to conversions all the same. If you need a WAV, switch tabs, change Format, switch back, then run.

**Can I close the tab while it runs?**
Yes. The job runs on the server and lands in your history when it finishes. Conversions collect in the History tab, newest first, each with its player and its download. The delete control there appears on jobs that did not finish; a completed conversion stays in your history.
