ictnlp/StreamSpeech Alternatives

1.3kPythonMITslowing · last push 1.3y agoGitHub

StreamSpeech is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.

What is known so far comes from the other direction:

Listed as an alternative to

These projects were analysed and named StreamSpeech among their alternatives. The relationship is not symmetric — how StreamSpeech rates them is a separate judgement, made when StreamSpeech is analysed in its own right.

k2-fsa/sherpa-onnxGitHub

calls StreamSpeech “Use when you need an all-in-one simultaneous speech recognition/translation/synthesis model and can accept a research-oriented Python package.”

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

14.5kC++active

PaddlePaddle/PaddleSpeechGitHub

calls StreamSpeech “All-in-one simultaneous ASR/ST/TTS model; choose for simultaneous speech tasks in one model.”

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.

12.7kPythonactive

abus-aikorea/voice-proGitHub

calls StreamSpeech “Choose for a research all-in-one simultaneous speech recognition/translation/synthesis model if you need an experimental end-to-end solution.”

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

12.6kPythonactive

moonshine-ai/moonshineGitHub

calls StreamSpeech “choose when you need simultaneous/offline speech recognition and synthesis in one research model and can run on GPU.”

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

10.9kC++active

espnet/espnetGitHub

calls StreamSpeech “Choose when you need a seamless unified model for offline/simultaneous ASR, translation, and synthesis to avoid using separate ESPnet components.”

End-to-End Speech Processing Toolkit

9.9kPythonactive

microsoft/VibeVoiceGitHub

calls StreamSpeech “a simultaneous speech recognition/translation/synthesis model; narrower than VibeVoice for long-form diarized ASR”

Open-Source Frontier Voice AI

53.1kPythonactive

speechbrain/speechbrainGitHub

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

A PyTorch-based Speech Toolkit

11.8kPythonactive