Phoneshift documentation

Phoneshift is a python package dedicated to voice/speech processing.

Features

  • High audio quality

  • Blazing fast

  • Super lightweight (can process hours long recordings without blowing up memory)

  • Fully tested (unit tests and audio regression tests)

  • Minimal dependencies (only numpy>=1.0)

  • Everything runs locally on your machine (no audio stream is sent to the cloud)

  • Neutral parameter leads to resynthesis identical to the original signal

  • Not introducing delays

Note

It assumes the signal is monophonic, like voice/speech, a flute, a violin, a saxophone, etc.

It is not recommended to use it on polyphonic signals like a piano, a guitar, a drum set, etc.

Dependencies and compatibility

  • numpy>=1.0 is the only package that will be installed along the phoneshift package.

  • Python 3.9+

  • Linux or Mac operating system.

  • 64bit architecture.

  • Network connectivity is required to validate an API token (status page).

Documentation

Disclaimer

THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.