AMV-TTS (Python)
Production-Grade 4-Tier On-Device Speech Synthesis Framework for Mobile & Edge (Zero-Dependency DSP Formant, C++ Vulkan GPU Neural Engine & Android Native Voice Bridge)
Installation
pip install amv-tts
1-Click Automated Engine Provisioning
amv-tts install --tier high
Quickstart
import amv_tts as tts
# 1. Studio Vulkan GPU Neural Engine
with tts.load(engine="vulkan", model_tier="high") as engine:
result = engine.synthesize("Neural speech synthesis on mobile GPU.", output="speech.wav")
print(f"Elapsed: {result.elapsed_ms:.1f}ms (RTF: {result.rtf:.4f}x)")
# 2. Zero-Dependency DSP Formant Mode
with tts.load(engine="dsp", preset="balanced") as engine:
result = engine.synthesize("Instant speech generation.", output="dsp.wav")
print(f"DSP Latency: {result.elapsed_ms:.1f}ms")
# 3. Direct Android Native Speaker Output
with tts.load(engine="native", language="en") as engine:
engine.speak("Direct hardware speaker output.")
Benchmarks (Physical Devices)
| Target Device | Hardware Architecture | Synthesis Engine | Real-Time Factor (RTF) | Status |
|---|---|---|---|---|
| Galaxy S25 | Snapdragon 8 Elite / Adreno 830 | Vulkan GPU (lessac-high-fp16) |
0.993x | Validated |
| Galaxy S25 | Snapdragon 8 Elite / Adreno 830 | Vulkan GPU (lessac-medium) |
0.264x | Validated |
| Galaxy A35 | Exynos 1380 / Mali-G68 MP5 | Vulkan GPU (lessac-medium) |
1.146x | Validated |
| ARM64 CPU | All Core Profiles | Parametric DSP Formant | 0.0130x | Validated |
Documentation
License
Apache-2.0 License. Copyright (c) 2026 Eunho Kim (@uno-km).
What's New in v1.7.0 — Tier 5 SOTA Neural Pipelines & Zero-Shot Voice Cloning
- Integrated Tier 5 SOTA ONNX neural synthesis pipelines: CosyVoice 2, F5-TTS, and ChatTTS INT8.
- Enabled on-device zero-shot voice cloning and conversational prosody control.
- Eliminated legacy sinusoidal fallback stubs in favor of strict fail-fast error reporting.
- Added speaker profile and acoustic adaptor CLI commands.
- Unified GPU neural vocoder dispatch through ameva-runtime HAL.
1 maintainer
Metadata
1 maintainer
Release files for amv-tts 2.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| amv_tts-2.0.0.tar.gz | 112.4 kB | Without provenance | Details for amv_tts-2.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| amv_tts-2.0.0-py3-none-any.whl | Python 3 | none | any | Details for amv_tts-2.0.0-py3-none-any.whl |
Total release size: 214.2 kB
Release files / amv_tts-2.0.0.tar.gz
| Download URL | amv_tts-2.0.0.tar.gz |
|---|---|
| Size | 112.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d50b0b248dfb194f66c74bd97ae4d32d351914a00963a5897441ecd45d538db7
|
|
BLAKE2b-256 checksum How to use checksums |
4d61c17b04220443b23f6080a3b62d8f80ced8e77e95f9cbaf3c1e026381450d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.17
|
Release files / amv_tts-2.0.0-py3-none-any.whl
| Download URL | amv_tts-2.0.0-py3-none-any.whl |
|---|---|
| Size | 101.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
435ba3f1bc7fb3af57ba20383d145ffc4eba4406e2b015231f4687f03a501847
|
|
BLAKE2b-256 checksum How to use checksums |
5f0dbbbdc44c37abd307764a90e8bb23aa71eecb5c113a9a296c199f3bfbafc9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.17
|
Security for amv-tts 2.0.0
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.
