# Avatar 101: Negative voice examples

URL: https://www.atmee.ai/docs/guides/negative-voice-examples

> The voice samples that make an avatar sound flat or wrong, each with a clip to listen to and the fix. Most problems are in how the sample is read, not in the microphone.

Your avatar speaks the way your voice sample does. This page lists only what goes wrong, with a
short clip of each problem, so you can rule it out. Anything not on it is fine.

A good sample is 10 to 60 seconds of one person speaking clearly; 15 to 30 seconds is plenty.
Formats and size limits are in [Create an avatar](/docs/api/create-avatar).

Every clip is an invented voice with one problem added, so that the problem is
the only thing that differs. Speak in your own way: any accent, language, pace
or style works.

## Why the voice matters

The voice sample drives more than how the avatar sounds:

* **Lip sync.** The avatar's mouth moves to its voice. A flat, quiet or muffled sample is a common
  reason the lips barely move or fall out of time with the words.
* **How the avatar comes across.** Its energy, warmth and character on every call come from your
  sample. A tired or monotone read gives an avatar that sounds bored, however good the portrait is.
* **Generation.** Atmee builds the avatar's talking clips from your portrait and voice together.
  A noisy or mixed sample can make the takes stiff or wrong, and Atmee refuses a sample shorter
  than 10 seconds or longer than 60.

## How each problem is marked

* **Won't work:** Atmee refuses the sample.
* **Likely to fail:** the avatar usually sounds or moves wrong.
* **May work:** try it, and listen to the result.

## Delivery

The most common problem isn't the microphone: it's a sample read without life. A voice that rises
and falls, stresses the words that matter and sounds like it means what it says gives an avatar
that does the same, with lips that move clearly. Read flat, and every answer comes out flat.

- **Read in a flat, even voice** (Likely to fail). The avatar speaks the way your sample does. With little rise and fall, the voice sounds bored and the lips barely move. Talk the way you would to a friend: let your voice rise on questions, fall at the end of a sentence, and lean on the words that matter. [Listen to the example](/docs/voice-examples/flat-monotone.mp3)
- **Tired and listless** (Likely to fail). Low energy carries straight into the voice, so every answer sounds like the end of a long day. Record when you feel awake, sit or stand up straight, and speak a little louder and livelier than feels natural. [Listen to the example](/docs/voice-examples/low-energy.mp3)
- **Each word read on its own** (Likely to fail). Reading word by word, or reading out a list, gives the voice a choppy, robotic rhythm. Speak in whole sentences, as if you were explaining something. Tell a short story or talk freely instead of reading items out. [Listen to the example](/docs/voice-examples/word-by-word.mp3)

## Recording

- **Shorter than 10 seconds** (Won't work). There is too little speech to learn a voice from, and Atmee refuses a sample under 10 seconds. Record 15 to 30 seconds; anything from 10 to 60 seconds works. [Listen to the example](/docs/voice-examples/too-short.mp3)
- **Longer than 60 seconds** (Won't work). Atmee refuses a sample over 60 seconds. Trim it to your best 15 to 30 seconds.
- **Someone else speaks in part of the file** (Likely to fail). The voice is learned from everyone in the file, so the avatar can drift between two people. Cut the other person's part out and keep only your own speech. [Listen to the example](/docs/voice-examples/other-speaker.mp3)
- **Two people talking at the same time** (Likely to fail). Overlapping voices can't be pulled apart, so the voice comes out muddled. Record again on your own, in a quiet room. [Listen to the example](/docs/voice-examples/overlapping-speakers.mp3)
- **Music under the voice** (Likely to fail). The music is learned as part of your voice and comes back as hum and warble. Record with no music playing. [Listen to the example](/docs/voice-examples/background-music.mp3)
- **Background noise** (Likely to fail). Chatter, traffic or a fan is learned along with your voice, and loud noise fails Atmee's check. Record somewhere quiet, with windows closed and fans off. [Listen to the example](/docs/voice-examples/background-noise.mp3)
- **Too quiet** (Likely to fail). A quiet recording is mostly room sound. Atmee may refuse it, and the voice comes out thin. Hold the microphone or phone closer, about a hand's width from your mouth. [Listen to the example](/docs/voice-examples/too-quiet.mp3)
- **Too loud and distorted** (Likely to fail). The crackle is learned too, so it comes back in every word the avatar says. Move the microphone a little further away or turn the input level down, then record again. [Listen to the example](/docs/voice-examples/clipped.mp3)
- **Long silences** (Likely to fail). Long pauses leave too little speech, and silence at the start or end can fail Atmee's check. Trim the silence at the start and end, and keep pauses short. [Listen to the example](/docs/voice-examples/long-silences.mp3)
- **Muffled or far from the microphone** (May work). A muffled or distant voice loses the detail the voice needs, so the avatar sounds dull. Speak towards the microphone from close by, without covering it. [Listen to the example](/docs/voice-examples/unclear-voice.mp3)
- **Room echo** (May work). The echo becomes part of the voice, so the avatar always sounds like it is in a bathroom. Record in a room with soft furnishings, like a bedroom, not a bare kitchen or hallway. [Listen to the example](/docs/voice-examples/room-echo.mp3)
- **Phone-call quality** (May work). A recorded call is thin and narrow, and the voice keeps that sound. Record with your phone's voice memo app, not over a call. [Listen to the example](/docs/voice-examples/phone-quality.mp3)

## If the result isn't right

Replace the voice sample with a new one. A new voice builds a new version of the avatar, and you can
switch back to the earlier one.

[How to optimize your avatar](/docs/guides/optimize-your-avatar) says which fix to try first for
what you see and hear.

- [Avatar 101: Negative image examples](/docs/guides/negative-image-examples): The portraits that animate badly, and what to use instead.
- [How to optimize your avatar](/docs/guides/optimize-your-avatar): What to try when an Atmee V2 avatar looks or sounds wrong.
- [Create an avatar](/docs/api/create-avatar): Build one through the API, with a portrait, a voice and a persona.
