Home/Speech & Audio/StreamSpeech

StreamSpeech

ictnlp/StreamSpeech

All-in-one speech recognition and synthesis model for offline and simultaneous processing

GitHub Website

GraphCanon updated 3w · GitHub synced 3w

1.3k stars103 forksLast push 1y Python MIT

Decision brief

StreamSpeech offers an all-in-one solution for offline and simultaneous speech recognition, translation, and synthesis in Python, utilizing PyTorch.

Good fit when

Use StreamSpeech when you need a compact model that can handle speech recognition, translation, and synthesis simultaneously without relying on online services.
Utilize this tool if your project requires non-autoregressive processing for efficient real-time applications, like live transcription or voice-to-voice translation.

Avoid when

Do not use StreamSpeech in scenarios where online connectivity is required due to its offline processing nature.
Avoid it when the target application demands autoregressive models, as StreamSpeech focuses on non-autoregressive techniques which might offer different performance characteristics.

Observed Jul 14, 2026 · Source: enrich:decision_facts

StreamSpeech alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (395d since push); As of 3w
Provenance: Not a fork · Organization account; As of 3w
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install StreamSpeech

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Speech

A scalable generative AI framework for Speech AI

18k★

speech-to-speech

Build local voice agents with open-source models

8.2k★

STT

A fast open-source deep-learning toolkit for speech-to-text

2.6k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

StreamSpeech offers seamless integration of speech recognition, translation, and synthesis capabilities.

Capability facts

Languages: python
Source: github.language · Jul 30, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 30, 2026)

- Python == 3.10, PyTorch == 2.0.1, Install fairseq & SimulEval

Source link

README

⚙Requirements

Python == 3.10, PyTorch == 2.0.1, Install fairseq & SimulEval

cd fairseq
pip install --editable ./ --no-build-isolation
cd SimulEval
pip install --editable ./

For agents

This page has a .md twin and JSON over the API.

/tools/ictnlp-streamspeech.md GET /api/graphcanon/tools/ictnlp-streamspeech GET /api/graphcanon/graph?tool=ictnlp-streamspeech