---
title: "Transcription errors"
description: "Transcription fails most often on an unsupported format, a file with no audio track, or a recording that exceeds your plan limit."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.speakai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcription errors

### File format not supported

Speak AI supports most common audio and video formats including MP3, MP4, WAV, M4A, WEBM, OGG, FLAC, and more. If your file is in an unusual format, try converting it to MP3 or MP4 first using a free tool like [HandBrake](https://handbrake.fr/) (video) or [Audacity](https://www.audacityteam.org/) (audio).

### File is too large

Files up to 4 hours in length are supported. If your file is very large, try compressing the audio bitrate. Reducing from 128kbps to 64kbps significantly decreases file size without noticeable loss in speech clarity.

### Audio quality is too low

If the audio is very quiet, heavily distorted, or has excessive background noise, the transcription engine may not be able to detect speech. Try:

- Recording in a quieter environment
- Using a dedicated microphone instead of a laptop mic
- Placing the recording device closer to the speakers

### Corrupted or incomplete file

If a recording was interrupted or the file was partially downloaded, it may be corrupted. Try re-downloading or re-recording the file.

### Server timeout

Very long files (2+ hours) occasionally time out during processing. If this happens, the file will usually complete on retry.

## Retry

1. Go to your media file in the [dashboard](https://app.speakai.co/dashboard)
1. Click the options menu on the file
1. Select **Re-transcribe** or **Re-analyze**

If the file fails again after retry, send us a message with the file name and we will investigate.

## Why this happens

By default, Speak AI auto-detects the language of each recording. Detection can land on the wrong language when a file is short, has music or noise at the start, or mixes languages. When that happens, the transcript comes back in the wrong language. You have three ways to control it.

## 1. Set the language at upload

On the upload screen, each file has a **Language** setting in the file list. It defaults to **Auto-detect**. Open it and choose the correct language before you start processing, and Speak AI will transcribe in that language.

## 2. Save a default language

If you mostly work in one language, save it so every new upload starts there instead of relying on auto-detection:

1. Go to [Profile > Account Preferences](https://app.speakai.co/profile/preferences).
1. Set **Media Language** to your language. This is the default source language for transcription and analysis of your uploads.

## 3. Re-transcribe a file you already uploaded

If a file already processed in the wrong language, re-transcribe it:

1. Open the media file and choose **Re-transcribe** from the actions menu.
1. Set the **Target Language** and confirm.

Re-transcribing creates a new version of the media and runs the full pipeline again, so it uses transcription hours just like a new upload.

## Tips for accurate detection

- Make sure speech starts early in the file. Long musical or silent intros throw detection off.
- For mixed-language recordings, set the dominant language manually instead of using Auto-detect.

The fastest way to reach us is the live chat in the app (the chat bubble in the bottom corner). You can also email [success@speakai.co](mailto:success@speakai.co).

Still stuck? Write to success@speakai.co or [book a free consult](https://calendly.com/speak-ai/consult?utm_source=docs&utm_campaign=consult).

---
Related: [Troubleshooting](/help/troubleshoot/) · [Export errors](/help/troubleshoot/exports/)

Source: https://docs.speakai.co/help/troubleshoot/transcription/index.mdx