speechbrain/speechbrain Alternatives

Choose when you prefer ESPnet's mature, recipe-driven PyTorch toolkit with extensive ASR/TTS support.

End-to-End Speech Processing Toolkit

Choose when you want NVIDIA's PyTorch speech toolkit with tight integration across ASR, TTS, and the NeMo ecosystem.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Choose when you need a low-latency C++ voice agent runtime rather than a PyTorch research toolkit.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

Choose when you work in PaddlePaddle and need an easy all-in-one speech pipeline.

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 Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Choose when you're building a Swift/CoreML Apple app and need on-device audio models.

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Choose when you want a Swift/MLX speech stack for Apple Silicon with no Python dependency.

AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML

Choose when you need lightweight offline inference on embedded/edge devices with ONNX models.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

Choose when you want a TensorFlow sequence-modeling framework with built-in speech research components.

Lingvo

Choose when you need very small-footprint offline ASR/VAD on edge devices using ncnn.

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

Choose when you need a lightweight, multi-platform offline ASR API without training your own models.

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Choose when your focus is ASR and you want streaming, VAD, punctuation, and scalable serving all in one box.

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Choose when you need a production-ready streaming ASR toolchain with a simple deployment story.

Production First and Production Ready End-to-End Speech Recognition Toolkit

Choose when you want a ready-made multilingual ASR model with emotion/language ID and no training.

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

Choose when you want a single pre-trained model for simultaneous speech recognition/translation/synthesis.

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Choose when your task is speech enhancement/separation/target speaker extraction and you don't need the rest.

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Choose when you need a dedicated, modular speaker diarization library with strong pretrained pipelines.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Choose when you need a simple, standalone STT training/decoding toolkit and can tolerate an older codebase with limited activity.

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

Choose when you specifically want Kaldi-style hybrid ASR with PyTorch and are okay with a stale project.

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

Choose when you need pretrained speaker verification/diarization models and not the broader speech toolkit.

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Choose when you want a standalone local STT app with LLM post-processing, not a library.

Fully local, private and cross platform Speech-to-Text with LLM Post-processing