Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

realtimetts-breeze-native

This repository distributes the pinned Vulkan Breeze worker used by RealtimeTTS. The wheel includes a shell-free launcher, native build provenance, and third-party notices. End users install a platform wheel; they do not need a C++ compiler, CMake, Vulkan SDK, or local native build.

The 0.1.0rc8 packages are TestPyPI candidates. Release wheels are built by CI from a tagged commit on main and published with tools/release.py, which checks their build-info against build_package.py. Model weights, credentials, GPU drivers, and vendor ICDs are never included.

Supported targets

The first candidate targets Windows x64 (win_amd64) and Linux x64. Linux wheels are built on Ubuntu 22.04 and repaired to manylinux_2_35_x86_64 after auditwheel inspection. macOS and ARM wheels are outside this package contract.

The worker uses the patched control path, Vulkan, and static Breeze/ggml components. MP3, CUDA, CLI, tests, and GGML_NATIVE are disabled. The tested model contract is the official Q8_0 model; Breeze model use remains subject to its research and non-commercial licence. A host Vulkan loader, driver, and ICD are required. Windows build output DLLs beside the worker are copied and hashed in build-info.json, except the system Vulkan loader. Linux auditwheel may vendor an ELF loader dependency; release evidence records the actual show and repair output.

Install and run on Windows or Linux

The end-user preview is installed from TestPyPI with uv. A compiler, Git checkout and local wheel files are unnecessary. After the preview is published:

uv venv --python 3.11 .venv-breeze
uv pip install --python .venv-breeze --find-links https://test.pypi.org/simple/realtimetts/ --find-links https://test.pypi.org/simple/realtimetts-breeze-native/ "realtimetts[breeze-server]==0.9.0rc23"
uv run --no-project --python .venv-breeze python -m RealtimeTTS.breeze_server --reference-prefix-cache --port 18086

Open http://127.0.0.1:18086/studio after warmup and select a bundled voice. First startup downloads the pinned 3.6 GB Q8_0 model ; later starts reuse cached assets. RealtimeTTS starts and stops the native worker.

The complete Windows guide also provides Qwen CPU/GPU setup, readiness checks and a tiny Python streaming client.

To install only the worker:

uv pip install --python .venv-breeze --find-links https://test.pypi.org/simple/realtimetts-breeze-native/ "realtimetts-breeze-native==0.1.0rc8"
uv run --no-project --python .venv-breeze python -c "from realtimetts_breeze_native import executable_path; print(executable_path())"

On Linux x86-64 with an NVIDIA GPU, the separate CUDA 12 worker is faster (realtimetts-breeze-native-cuda12==0.1.0rc8, or realtimetts[breeze-server,breeze-cuda] with --find-links https://test.pypi.org/simple/realtimetts-breeze-native-cuda12/). It needs only the NVIDIA driver; the CUDA runtime and cuBLAS come from NVIDIA's wheels.

The native package does not download weights. Model caching and --download-model belong to RealtimeTTS.

Maintainer build

build_native.py clones the exact upstream revision, initializes its exact ggml submodule, applies tools/breeze_cpp_controls.json, configures CMake, builds breeze-server, stages provenance, and creates an sdist plus platform wheel. Source, build, and stage directories default outside this checkout.

Linux CI downloads and verifies LunarG Vulkan SDK 1.3.296.0 through the official versioned endpoint, then repairs the wheel with auditwheel. Windows CI uses Winlibs GCC 12.2.0 and MSYS2 shaderc 2026.3, glslang 16.3.0 and Vulkan 1.4.357.0. The exact archive names and SHA-256 hashes are pinned in tools/install_windows_toolchain.py. These reproduce the working Windows compiler and shader tools while keeping GGML_NATIVE=OFF. See .github/workflows/ci.yml for the complete reproducible build commands. Users of the wheels need neither SDK nor compiler.

Use --source-dir only for a clean checkout at the pinned revision. The lower level build_package.py assembler accepts only a completed Release CMake build, the exact controls patch, and an empty stage outside this repository.

Pinned inputs

  • Breeze-TTS-2.cpp: v0.1.6, 87b43667ca5597f826441991e416a279ed7373b9
  • ggml: 36da57138425487184aa1da2eee2cde155909c6f
  • SPIRV-Headers (vulkan-sdk-1.3.296.0): 2a9b6f951c7d6b04b6c21fe1bf3f475b68b84801
  • controls SHA-256: bfba1d1640da1f1c87d192a61fe8da86e4e92c334e21a5cbf151cb48335e9831 (0.1.0rc8; rc7: 4e9f771e…5b79, rc4: 12c938d1…25e9b3)

Read bundled notices before redistribution. The model licence is separate from the package licence.

Breeze v0.1.6 (0.1.0rc8)

rc8 moves the pinned source from a0e177f (September) to upstream v0.1.6:

  • The vocoder keeps its state between flushes and decodes only new frames, and it upsamples with a matmul. Upstream measures about 6.6 -> 2.4 ms per frame on Vulkan.
  • The depth decoder runs all codebooks and their sampling in one GPU graph, about 30% faster per frame.
  • The first chunk sizes itself. --chunk-first is a floor: the worker starts with 1 frame when the GPU keeps well ahead of playback, and 2, 4 or 8 when it does not. Later flushes go out early when the listener is about to run dry.
  • The CUDA build turns on CUDA graphs (GGML_CUDA_GRAPHS).
  • --parallel N lets streams share one GPU batch per frame. The default stays 1.
  • Every request runs on one GPU thread (the upstream scheduler). The controls now live there too: stop and pause are polled between frames instead of blocking, a paused stream holds its slot and takes no frames, and the paused event follows the audio already sent. The reference-prefix cache is lent to one stream at a time, and a second stream in the same batch prefills in full.
  • The rc3 second-chunk rule is gone; the upstream ramp and early flush replace it.
  • Upstream now embeds the WebUI as byte arrays, so the bounded embed script this package used to install is no longer needed.

GPU prewake (0.1.0rc7, first released in 0.1.0rc8)

The controls add an opt-in prewake stream message, sent before the first text: the worker runs 4-frame vocoder passes on silent codes, the size of the first real chunk, until text arrives, the stream is cancelled or closed, or max_ms passes (default 1500, maximum 5000). Since rc8 each pass runs on the GPU thread only while no stream is queued or generating, so it never delays speech on any connection. It ends with a prewake_done event, and /health reports gpu_prewake. It keeps an idle Windows GPU from starting a reply at idle clocks (RealtimeTTS and Miep use it only when the server advertises it).

Voice registration waits for the GPU (up to 2 s) instead of answering 409 at once, and prewake passes skip the GPU while it waits. In rc5 the back-to-back passes made registrations fail with 409 while the user paused.

A synthesis that has to wait for the GPU counts as a waiter too, so a prewake on another connection stops taking the GPU. In rc6 such a synthesis waited behind the whole prewake (measured: 1281 ms to first PCM, against 281 ms on the woken connection and 563 ms with no prewake).

CUDA 12 worker (0.1.0rc4)

0.1.0rc4 rebuilds the unchanged rc3 source and control patch and adds realtimetts-breeze-native-cuda12 for Linux x86-64: the same worker built with CUDA for architectures 86, 89, 90 and 120 (machine code for each, PTX for 120). On an RTX 4090 it reached the first audible sample about 35 ms sooner than the Vulkan worker. Both packages come from one tagged commit and CI run.

Early streaming cadence (0.1.0rc3)

The second chunk stays small before resuming the existing ramp. With the default first4/max6 profile this produces 4, 4, 6, 6 frames. The first chunk and steady-state chunk size are unchanged; the second chunk arrives earlier to preserve headroom when pitch-preserving tempo processing retains some audio. No playback buffer is added. Native per-request timings remain in WebSocket metrics; redundant console writes no longer block completion and the tempo tail.

Portable performance build (0.1.0rc2)

Both platform wheels include the reference-prefix cache, bounded cross-sentence context, cache invalidation and native timing metrics from the working runtime. These are shared source changes; GGML_NATIVE stays OFF. No machine-specific CPU affinity masks, thread counts or GPU device IDs are embedded in the wheels. Enable the reference-prefix cache through the RealtimeTTS Python server option --reference-prefix-cache. Vulkan drivers remain a host requirement.

Metadata

Release files for realtimetts-breeze-native 0.1.0rc8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for realtimetts-breeze-native 0.1.0rc8
File Size Uploaded Provenance Actions
realtimetts_breeze_native-0.1.0rc8.tar.gz 52.5 kB Without provenance Details for realtimetts_breeze_native-0.1.0rc8.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for realtimetts-breeze-native 0.1.0rc8
File Interpreter ABI Platform Actions
realtimetts_breeze_native-0.1.0rc8-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for realtimetts_breeze_native-0.1.0rc8-py3-none-win_amd64.whl
realtimetts_breeze_native-0.1.0rc8-py3-none-manylinux_2_35_x86_64.whl Python 3 none Linux glibc 2.35+ x86-64 Details for realtimetts_breeze_native-0.1.0rc8-py3-none-manylinux_2_35_x86_64.whl

Total release size: 35.0 MB

Release files / realtimetts_breeze_native-0.1.0rc8.tar.gz

Download URL realtimetts_breeze_native-0.1.0rc8.tar.gz
Size 52.5 kB
Tags Source
SHA-256 checksum
How to use checksums
8d95948790285a3c1bd1838239b10628c7647582d425616bd5b11e87786329ab
BLAKE2b-256 checksum
How to use checksums
77528a6af03e345bc2e3df9cec70aa58e157a2948e8b077daf17b397b49b5b4a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Release files / realtimetts_breeze_native-0.1.0rc8-py3-none-win_amd64.whl

Download URL realtimetts_breeze_native-0.1.0rc8-py3-none-win_amd64.whl
Size 18.3 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
e42e3f1c494af6011ce7cc10f58914e0c74d34d757593dd5a6c2dde5c7f5fea8
BLAKE2b-256 checksum
How to use checksums
16537e7d3151b77dfc00a5f43dd6318ce4c43f2335fa22214e91f39fd72cf822
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Release files / realtimetts_breeze_native-0.1.0rc8-py3-none-manylinux_2_35_x86_64.whl

Download URL realtimetts_breeze_native-0.1.0rc8-py3-none-manylinux_2_35_x86_64.whl
Size 16.6 MB
Tags Linux glibc 2.35+ x86-64 Python 3
SHA-256 checksum
How to use checksums
d3bcc3ceba7990b2c85927e0ccf22a34b69deca02937f4aeb5d4a98d7c8b78c0
BLAKE2b-256 checksum
How to use checksums
fda8ce15f36efd7814940febfe2e442b909cafc89b43278fd69be6319ce8f578
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.4

Security for realtimetts-breeze-native 0.1.0rc8

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page