OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Parrots

Parrots is an Apache-2.0 Python toolkit for automatic speech recognition and text-to-speech. It includes ASR and synthesis examples, multilingual model support, streaming TTS and IndexTTS2 options for speaker, emotion and duration controls.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Parrots — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Parrots when building a Python application needs documented ASR or TTS workflows, particularly for Chinese, English or other listed supported languages.

Who it is for

  • Python developers adding speech recognition to an application.
  • Teams generating spoken output from text in multilingual experiences.
  • Developers exploring streaming speech output or controlled, expressive synthesis.

Documented uses

  • Convert a speech audio file into recognized text.
  • Generate a speech audio file from text.
  • Produce speech in chunks for a lower-latency output workflow.
  • Use reference audio or emotion controls in IndexTTS2 synthesis.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source under Apache-2.0. The README documents PyPI and source installation, and links to an online demo.

  • The README identifies distilwhisper for ASR and GPT-SoVITS for TTS.
  • Listed language examples include Chinese, English and Japanese; the project describes additional multilingual support.
  • Basic TTS examples specify a speaker model and speaker name.
  • The documented basic TTS example allows CPU or CUDA selection.
  • IndexTTS2 examples include reference-audio, emotion-vector and text-based emotion controls.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Parrots for Python speech workflows

Install the toolkit and its documented dependencies before using its ASR or TTS examples.

Before you start

  • Python 3.7 or newer
  • PyTorch
  • The repository's requirements file

Steps

  1. Install PyTorch using pip or conda.

  2. Install the dependencies listed in requirements.txt.

  3. Install parrots with pip, or clone the repository and run python setup.py install.

Expected outcome

The documented package or source installation is in place for working with Parrots examples.

Guide limitations

  • The installation instructions do not specify complete hardware requirements.
Documentation 1 ↗
Source-based practical guide

Recognize speech from a WAV file

Pass a WAV file to Parrots speech recognition and read the returned text.

Before you start

  • Parrots installed with its documented dependencies
  • A WAV file to process

Steps

  1. Import SpeechRecognition from parrots.

  2. Initialize it with SpeechRecognition().

  3. Call recognize_speech_from_file with the WAV file path.

  4. Read the returned text field.

Expected outcome

The example returns recognition text, illustrated with the output “北京图书馆”.

Guide limitations

  • The example documents file-based recognition; it does not specify broader input formats.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
shibing624/parrots · Official homepage title · retained in its source language
How we review sourcesSuggest a correction