Skip to content
Projects

ideapacket/voxwright has 31 GitHub stars and 242 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 03:35 UTC. Last push 2026-11-01.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
Collecting history
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

Offline voice-agent application layer: session core with byte-deterministic replay, spoken-LLM adapters (scripted/replay/loopback-mock), injection-safe function-call grammar, slot grounding, workflow engine with compensation and resume, permissioned tool sandbox, repair-dialog policies, task-success and latency evaluation. NumPy core, torch extra.

Machine Learning

README.md

Original

voxwright

voxwright 是一个 Python 3.11+ 离线工具箱,用于实现和验证端到端 spoken language model 接入应用时的工程机制:事件记录与重放、受约束工具调用、状态编排、权限、修复策略、 逻辑时钟延迟统计与合成场景评估。

项目只评估这些应用机制。默认测试与示例使用带有植入真值的合成数据和确定性适配器, 不连接真实模型端点,不需要 API key、预训练权重、外部数据集、GPU 或付费服务。

开始使用

uv venv .venv
uv pip install --python .venv/bin/python -e ".[dev]"
make test
.venv/bin/voxwright --help

完整的离线命令链、制品约束与退出码见 docs/cli.md。 可选 CPU 训练层的范围与验证方式见 docs/model-extra.md。

文档与示例

许可

项目使用 MIT License,详情见 LICENSE。