Verified project record

PaddlePaddle/PaddleSpeech

PaddleSpeech is an open-source speech and audio toolkit covering ASR, TTS, voice cloning, and audio classification. It runs locally via Python CLI and server components, and requires the PaddlePaddle framework as an external dependency.

Project overview

Project type: Audio & Speech
Use cases: Meeting Notes · Audio & Speech
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Developers who need a local, self-hosted Python toolkit for processing speech and audio tasks across ASR, TTS, and voice cloning.
Teams looking to run their own ASR and TTS server instances for handling speech requests.

Key capabilities

Converts input audio (such as 16k wav format) to text using state-of-the-art models, supporting streaming and code-switch scenarios.
Synthesizes audio from input text (outputting in 24k sample rate wav format) using a rule-based Chinese text frontend.
Clones voices using speaker encoder models including GE2E, VITS, and ECAPA-TDNN.
Recovers text punctuation and is designed to integrate with ASR model outputs.
Performs open-domain sound classification based on 527 categories from the AudioSet dataset.
Provides server and streaming server systems to serve ASR and TTS requests.

Limitations and risks

Speech Translation relies on pre-compiled Kaldi-related tools, restricting its use to the Ubuntu operating system.

Getting started

Setup is rated medium difficulty. Users need a Python environment and must install the external PaddlePaddle dependency separately. A quick start involves installing PaddlePaddle, installing PaddleSpeech, and running an ASR command on a Chinese wav file.

Evidence and sources

GitHub project description: Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End…
README: PaddleSpeech is an open-source toolkit on PaddlePaddle platform for a variety of critical tasks in speech and audio, with the state-of-art and influential models.
README: Via the easy-to-use, efficient, flexible and scalable implementation, our vision is to empower both industrial application and academic research, including training, inference & t…
README: Streaming ASR and TTS System: we provide production ready streaming asr and streaming tts system.
Release: PaddleSpeech r1.5.0

Reviewed at: 2026-07-18T00:46:41Z