wavhost 0.1.0__tar.gz

wavhost-0.1.0/CHANGELOG.md

@@ -0,0 +1,15 @@
+# Changelog
+
+All notable changes to Wavhost are documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.0] - 2026-09-14
+
+### Added
+
+- CLI: `pull`, `run`, `serve`, `list`, `rm`, and `uninstall`
+- OpenAI-compatible `POST /v1/audio/speech` HTTP API
+- Chatterbox backend with on-demand engine install
+- Ollama-style content-addressed local model storage

wavhost-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

wavhost-0.1.0/MANIFEST.in

@@ -0,0 +1,19 @@
+include LICENSE
+include NOTICE
+include README.md
+include CHANGELOG.md
+include pyproject.toml
+graft wavhost
+graft tests
+global-exclude *.py[cod]
+global-exclude __pycache__
+global-exclude *.so
+global-exclude .DS_Store
+prune env
+prune .pytest_cache
+prune wavhost.egg-info
+prune dist
+prune build
+exclude PRD-v2.md
+exclude REFACTORING.md
+exclude output.wav

wavhost-0.1.0/NOTICE

@@ -0,0 +1,4 @@
+Wavhost
+Copyright 2026 Wavhost Contributors
+
+This product includes software developed by Wavhost Contributors.

wavhost-0.1.0/PKG-INFO

@@ -0,0 +1,400 @@
+Metadata-Version: 2.4
+Name: wavhost
+Version: 0.1.0
+Summary: Local-first TTS runtime with OpenAI-compatible API
+Author: Wavhost Contributors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/smitgol/wavhost
+Project-URL: Documentation, https://github.com/smitgol/wavhost#readme
+Project-URL: Repository, https://github.com/smitgol/wavhost
+Project-URL: Issues, https://github.com/smitgol/wavhost/issues
+Project-URL: Changelog, https://github.com/smitgol/wavhost/blob/master/CHANGELOG.md
+Keywords: tts,text-to-speech,speech,local,runtime,openai,chatterbox
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: click>=8.1.0
+Requires-Dist: fastapi>=0.109.0
+Requires-Dist: uvicorn[standard]>=0.27.0
+Requires-Dist: pydantic>=2.5.0
+Requires-Dist: pydantic-settings>=2.1.0
+Requires-Dist: httpx>=0.26.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: torch>=2.0.0
+Requires-Dist: torchaudio>=2.0.0
+Provides-Extra: chatterbox
+Requires-Dist: chatterbox-tts>=0.1.0; extra == "chatterbox"
+Requires-Dist: setuptools<82; extra == "chatterbox"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.7.0; extra == "dev"
+Provides-Extra: publish
+Requires-Dist: build>=1.2.0; extra == "publish"
+Requires-Dist: twine>=6.1.0; extra == "publish"
+Dynamic: license-file
+
+# Wavhost
+
+[![PyPI](https://img.shields.io/pypi/v/wavhost.svg)](https://pypi.org/project/wavhost/)
+[![Python](https://img.shields.io/pypi/pyversions/wavhost.svg)](https://pypi.org/project/wavhost/)
+[![License](https://img.shields.io/pypi/l/wavhost.svg)](https://github.com/smitgol/wavhost/blob/master/LICENSE)
+
+**Local-first TTS runtime with OpenAI-compatible API**
+
+Wavhost is a local text-to-speech (TTS) runtime that brings high-quality voice synthesis to your machine. Run TTS models locally with a simple CLI and OpenAI-compatible HTTP API—no API keys, no per-character billing, complete privacy.
+
+## Features
+
+- 🚀 **Local-first**: All processing happens on your machine
+- 🔌 **OpenAI-compatible API**: Drop-in replacement for OpenAI's `/v1/audio/speech` endpoint
+- 📦 **Ollama-style storage**: Content-addressed model storage with deduplication
+- 🎯 **Simple CLI**: Pull, run, and serve models with ease
+- 🔓 **Open source**: MIT/Apache-2.0 licensed runtime, using open TTS models
+- ⚡ **GPU accelerated**: Optimized for NVIDIA GPUs (CPU fallback available)
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install wavhost
+```
+
+This installs the runtime and PyTorch. TTS engines such as Chatterbox are **not** included, since each one is large and Wavhost supports several — the engine a model needs is installed for you when you pull that model.
+
+**GPU users:** engines pin an exact PyTorch version, and PyPI's wheel for that pin is CPU-only on Windows. `wavhost pull` detects an NVIDIA GPU paired with a CPU-only PyTorch and prints the one command that swaps in the CUDA build while keeping the engine's pin, e.g.:
+
+```bash
+pip install "torch==2.6.0+cu124" "torchaudio==2.6.0+cu124" --index-url https://download.pytorch.org/whl/cu124
+```
+
+Run it *after* the pull (the engine install would otherwise replace it), and note the `+cu124` tag is required — pip considers `2.6.0+cpu` to already satisfy `torch==2.6.0`. The same hint appears if `wavhost run` ever has to fall back to the CPU.
+
+### Pull a Model
+
+```bash
+wavhost pull chatterbox-turbo
+```
+
+This displays the license, installs the model's backend engine if needed, and **downloads weight layers** into `~/.wavhost` (content-addressed blobs + a local checkpoint). Runtime loads from that local checkpoint — it does not call the Hugging Face Hub client.
+
+Layer URLs currently point at Hugging Face resolve endpoints as plain HTTPS. Swapping to your own CDN later only requires changing those URLs in the registry.
+
+If you'd rather manage engine packages yourself, install the matching extra ahead of time and skip the prompt:
+
+```bash
+pip install "wavhost[chatterbox]"
+wavhost pull chatterbox-turbo --skip-deps
+```
+
+### Generate Speech
+
+```bash
+wavhost run chatterbox-turbo "Hello world, this is Wavhost!" -o output.wav
+```
+
+### Start the Server
+
+```bash
+wavhost serve
+```
+
+The server starts on `http://127.0.0.1:11435` with an OpenAI-compatible endpoint.
+
+### Use the API
+
+```bash
+curl http://127.0.0.1:11435/v1/audio/speech \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "chatterbox-turbo",
+    "input": "Hello from Wavhost!",
+    "voice": "default"
+  }' \
+  --output speech.mp3
+```
+
+## Available Models
+
+| Model | Size | Device | Description |
+|-------|------|--------|-------------|
+| `chatterbox-turbo` | 350M | GPU | Fast, high-quality English TTS (MIT) |
+| `chatterbox-base` | 500M | GPU | Original high-quality model (MIT) |
+
+All models are licensed under MIT and developed by Resemble AI.
+
+## CLI Reference
+
+### `wavhost pull <model_name>`
+
+Download weight layers into local storage and register the model, installing its backend engine if needed.
+
+**Options:**
+- `--force`: Pull even if the model is already installed (still resumes existing blobs)
+- `--skip-deps`: Don't install the backend engine (assume it's already available)
+
+**Example:**
+```bash
+wavhost pull chatterbox-base
+```
+
+### `wavhost run <model_name> <text>`
+
+Generate speech from text using a local model.
+
+**Options:**
+- `-o, --output PATH`: Output WAV file path (default: `output.wav`)
+- `--voice PATH`: Reference voice audio for cloning (experimental)
+- `--device DEVICE`: Device to use (`cuda`, `cpu`, or `mps`)
+
+**Example:**
+```bash
+wavhost run chatterbox-turbo "Welcome to Wavhost" -o welcome.wav
+```
+
+### `wavhost serve`
+
+Start the OpenAI-compatible TTS server.
+
+**Options:**
+- `--host HOST`: Host to bind to (default: `127.0.0.1`)
+- `--port PORT`: Port to bind to (default: `11435`)
+- `--reload`: Enable auto-reload for development
+
+**Example:**
+```bash
+wavhost serve --host 0.0.0.0 --port 8000
+```
+
+### `wavhost list`
+
+List installed models and available models in the registry.
+
+**Example:**
+```bash
+wavhost list
+```
+
+### `wavhost rm <model_name>`
+
+Remove a pulled model and free its disk space (manifest, checkpoint, and any blobs no other model still uses).
+
+**Options:**
+- `-y, --yes`: Skip the confirmation prompt
+
+**Example:**
+```bash
+wavhost rm chatterbox-turbo
+```
+
+### `wavhost uninstall`
+
+Wipe local Wavhost data under `~/.wavhost` and print how to remove the Python package.
+
+**Options:**
+- `--purge-data` / `--keep-data`: Delete or keep local storage (default: purge)
+- `-y, --yes`: Skip the confirmation prompt
+
+**Example:**
+```bash
+wavhost uninstall
+# then, if you also want the package gone:
+pip uninstall wavhost
+```
+
+## API Reference
+
+### `POST /v1/audio/speech`
+
+Generate speech from text (OpenAI-compatible).
+
+**Request body:**
+```json
+{
+  "model": "chatterbox-turbo",
+  "input": "Text to synthesize",
+  "voice": "default",
+  "response_format": "mp3",
+  "speed": 1.0
+}
+```
+
+**Parameters:**
+- `model` (string, required): Model to use
+- `input` (string, required): Text to synthesize (max 4096 chars)
+- `voice` (string, optional): Voice identifier (default: "default")
+- `response_format` (string, optional): Audio format. Defaults to `mp3`.
+  - Encoded: `mp3`, `wav`, `opus`, `flac`, `aac`
+  - Raw PCM (signed 16-bit little-endian): `pcm` (model native rate), `pcm_16000`, `pcm_22050`, `pcm_24000`, `pcm_44100`
+- `speed` (float, optional): Speed multiplier 0.25-4.0 (currently not implemented)
+
+**Response:**
+Binary audio file in the requested format.
+
+### `GET /v1/models`
+
+List available models (OpenAI-compatible).
+
+**Response:**
+```json
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "chatterbox-turbo",
+      "object": "model",
+      "created": 0,
+      "owned_by": "resemble",
+      "installed": true,
+      "description": "Chatterbox Turbo - 350M parameter English TTS model (MIT License)"
+    }
+  ]
+}
+```
+
+### `GET /health`
+
+Health check endpoint.
+
+**Response:**
+```json
+{
+  "status": "ok"
+}
+```
+
+## Architecture
+
+### Storage
+
+Wavhost uses Ollama-style content-addressed storage:
+
+```
+~/.wavhost/
+  models/
+    manifests/
+      registry/
+        resemble/
+          chatterbox-turbo/
+            latest
+    blobs/
+      sha256-<hash>
+    checkpoints/
+      resemble/
+        chatterbox-turbo/
+          latest/
+            ve.safetensors
+            ...
+```
+
+- **Manifests**: Model metadata and layer digests
+- **Blobs**: Content-addressed file storage with SHA-256 deduplication
+- **Checkpoints**: Materialized directories (hardlinks/copies of blobs) loaded by `from_local`
+
+### Backends
+
+The `TTSBackend` protocol enables pluggable TTS engines:
+
+- **Chatterbox**: MIT-licensed models by Resemble AI (currently implemented)
+- Future backends can be added by implementing the `TTSBackend` protocol
+
+## Hardware Requirements
+
+### Recommended (GPU)
+- NVIDIA GPU with 4GB+ VRAM (RTX 2060 or better)
+- 16GB+ system RAM
+- CUDA 11.8 or newer
+
+### Minimum (CPU)
+- Modern CPU with 8+ cores
+- 8GB+ system RAM
+- Generation falls back to CPU automatically, but runs considerably slower than real-time
+
+## Development
+
+```bash
+git clone https://github.com/smitgol/wavhost.git
+cd wavhost
+pip install -e ".[dev]"
+```
+
+### Running Tests
+
+```bash
+pytest
+```
+
+### Code Quality
+
+```bash
+# Format code
+black wavhost tests
+
+# Lint
+ruff check wavhost tests
+
+# Type checking
+mypy wavhost
+```
+
+## Roadmap
+
+### v0.1 (Current)
+- ✅ Ollama-style storage
+- ✅ Chatterbox backend
+- ✅ CLI (pull, run, serve)
+- ✅ OpenAI-compatible API
+
+### Future
+- Additional backends (Qwen3-TTS, etc.)
+- Voice cloning support
+- Streaming audio generation
+- Model quantization
+- Multi-language models
+
+## License
+
+**Wavhost (this runtime):** Apache-2.0
+
+**Third-party models:** Each model is subject to its own license:
+- Chatterbox models: MIT License (see [Resemble AI's license](https://github.com/resemble-ai/chatterbox/blob/main/LICENSE))
+
+Model licenses are displayed before download with `wavhost pull`.
+
+## Contributing
+
+Contributions welcome! Please feel free to submit issues and pull requests.
+
+## Acknowledgments
+
+- [Resemble AI](https://resemble.ai) for the excellent Chatterbox TTS models
+- [Ollama](https://ollama.ai) for storage architecture inspiration
+- [OpenAI](https://openai.com) for the audio API specification
+
+## Support
+
+- 📖 [Documentation](https://github.com/smitgol/wavhost)
+- 🐛 [Issue Tracker](https://github.com/smitgol/wavhost/issues)
+- 💬 [Discussions](https://github.com/smitgol/wavhost/discussions)
+
+---
+
+**Built for developers who want local, private, high-quality TTS.**