---
name: "tonetrain"
section: "1"
platform: "linux"
package: "vpb-utils"
version: "4.2.61-1.4"
release: "Debian 12 (Bookworm)"
platforms: ["linux"]
url: "https://new.carta.tech/tonetrain"
---

# tonetrain(1)

Analyse telephony signal tones for the libvpb programmable detector

## NAME

tonetrain - Analyse telephony signal tones for the libvpb programmable detector

## SYNOPSIS

**tonetrain** \[*options*\] *file*

## DESCRIPTION

The **tonetrain** utility analyses a recorded signal from *file* to determine the best tone detector parameters for recognising it.

## OPTIONS

The following options are available:

- **-V**

  Be more verbose during execution.

### Input options

- **-w**

  Use wav file format for input.  This is the default.

- **-v**

  Use vox file format for input.

- **-s** sec

  Skip the first *sec* seconds of the recording.  Useful if the tone does not begin cleanly at the start of the recording.

- **-t** sec

  Train using *sec* seconds of the recording.  Useful if only a portion of the recording actually contains the desired to to train for.

### Output options

- **-p**

  Output the results in plain english.  This is the default.

- **-e**

  Output the results in a form suitable for use with the VPB\_TONE enviroment variable for libvpb.

- **-c**

  Output the results as a C source code snippet.

## SEE ALSO

[**tonedebug**(1)](/tonedebug/1.md)

## AUTHOR

Ron Lee, Ben Kramer, David Rowe, Voicetronix \<support@voicetronix.com.au\>

This manual page was written by Ron \<ron@debian.org\>, for the Debian project (but may be used by others).