Vokra

English | 日本語

Vokra is a speech-first inference runtime written in Rust. It implements the audio pieces that general-purpose graph runtimes often leave to application code: streaming state, STFT/iSTFT and mel frontends, vocoders, neural codecs, CTC/RNN-T decoding, VAD, speaker features, pitch extraction, and audio enhancement.

Vokra loads provenance-aware GGUF files and does not load ONNX graphs at runtime. The default runtime has no third-party Cargo dependencies: the root Cargo.lock contains only first-party vokra-* crates.

CPU preview: v0.4.0-rc.1 is available for evaluation. The published Linux CLI has functional checks for fixed Whisper base ASR and Silero VAD v5 models. See the installation guide for exact files and limitations. This does not establish numerical parity, performance, other-OS model inference or full-catalog Apple Metal support. Current project status tracks releases, source, PRs and remaining work.

Why Vokra

• Audio-native execution: speech frontends, streaming caches, decoders, vocoders, codecs, VAD, and enhancement are native operators rather than ONNX graph glue.
• Small dependency surface: runtime crates depend only on first-party vokra-* crates. Offline conversion remains separate from runtime loading.
• Explicit failures: unsupported operations and unavailable devices return errors; GPU work never silently falls back to CPU.
• Reproducible model files: Vokra GGUF metadata records frontend settings, topology, quantization policy, source provenance, and licence information.
• Portable integration: CPU is the default; Metal, CUDA, Vulkan, and WebGPU are opt-in. A generated C header supports native and language bindings.

Quick start

Choose the guide for your task:

Task	Guide
Try the verified prebuilt CPU preview	Preview installation
Build from source and convert checkpoints	Getting started
Use model-specific CLI options and formats	CLI tutorial

Model and backend status

A converter, a GGUF binder, native inference, independent numerical parity, publication and real-device validation are separate milestones. A listed model or successful build does not establish all of them. Use current status for the dated inventory and outstanding work, and model cards for artifact-specific terms.

CPU is the default. Accelerator support is optional and operation-specific; see the backend guide and architecture. Unsupported operations and unavailable devices return errors instead of silently falling back to CPU.

Library integration

Build the C library with:

cargo build --release -p vokra-capi

include/vokra.h is the generated C reference. The API index links to the Rust and binding surfaces, including Python, Swift/iOS, Unity, Godot, Android, web, and server examples. The C ABI remains pre-1.0 and is not frozen.

Documentation

• Documentation map
• Getting started
• CLI tutorial
• Architecture
• Backend guide
• Migration guide
• Licence audit and legal/compliance notes

Contributing

Contributions are welcome. Read CONTRIBUTING.md before a large change, and use the good first tasks for scoped entry points. Bugs and proposals can be filed in GitHub Issues. Participation is governed by the Code of Conduct. Report vulnerabilities privately as described in the Security Policy, not in a public issue.

Licence

Vokra source code is licensed under Apache-2.0. Model weights and reference assets may use different licences; review each model card, docs/license-audit.md, and NOTICE before redistribution or commercial use. Non-commercial weights are excluded from the default publication path unless an explicit research-only gate is used.