ictnlp/StreamSpeech
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
This project helps anyone who needs to quickly understand or communicate across different languages in real-time. It takes spoken language in one language and can instantly transcribe it, translate it to text, or translate it to spoken language in another language. It's designed for professionals like international communicators, multilingual content creators, or those facilitating cross-cultural discussions who need immediate, accurate translation.
1,252 stars. No commits in the last 6 months.
Use this if you need an "all-in-one" solution for converting speech to text, translating speech to text, or translating speech to synthesized speech, whether offline or simultaneously.
Not ideal if your primary need is for advanced visual translation, multimodal interactions beyond speech, or if you require support for a very niche language pair not commonly covered.
Stars
1,252
Forks
102
Language
Python
License
MIT
Category
Last pushed
Jun 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ictnlp/StreamSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
speechmatics/speechmatics-python
Python library and CLI for Speechmatics
gooofy/py-nltools
A collection of basic python modules for spoken natural language processing
IBM/MAX-Speech-to-Text-Converter
Converts spoken words into text form.
snakers4/open_stt
Open STT
verbio-technologies/python-verbio-speech-center
Python integration with the Verbio Speech Center Cloud. https://speechcenter.verbio.com/