97e9572f42
Apps ask the hub for a recognizer or a voice and get one; where it runs is the hub's decision. AiHub::start_stt / start_tts return poll-driven sessions shaped like the chat session. The Auto ladder is Whisper/Kokoro in this process (weights present, machine election), on the machine node over loopback, on a LAN node, else the OS engine; SpeechReach::Local is the "don't reach out" knob. Audio always comes back as PCM: the app owns the device. Three layers: - makepad-ai-speech is the whole speech model family, engines only. libs/voice (Whisper + Silero VAD) folds in as the `whisper` and `vad` modules next to kokoro and indextts, each a cargo feature; the Apple bridges and the Speaker/VoiceTranscriber selection leave it. - makepad-system-speech (new) is the OS speech services as blocking fns: Apple SpeechAnalyzer/AVSpeechSynthesizer via Swift, Windows.Media.Speech* on the vendored bindings, Android SpeechRecognizer/TextToSpeech through MakepadSpeech.java (API 26 floor), espeak-ng on Linux. It models the two STT shapes honestly: PCM in (Whisper, Apple) versus an engine that owns the microphone (Android, Windows), with capabilities the caller reads. - the hub grows speech sessions, in-process Whisper/Kokoro workers with the residency election, a `whisper` wire backend (stt domain, registry entry pinned to ggerganov/whisper.cpp) so a Mac can serve a Quest, and a `language` field on the generate request. Consumers: the Window voice input runs on an STT session and switches to engine-mic mode when the recognizer owns the microphone; converse's SpeechOutput is a lazily started TTS session plus a pump thread; route drops its private speech copy for converse; vj's lyrics fallback and the alignment bakes call the engines directly. Verified here: speech-roundtrip through the real sessions (Apple voice in, in-process Whisper on Metal out, 4.3% WER); system-speech-test TTS->STT verbatim; hub/converse/system-speech unit tests; msvc, aarch64-android and linux-gnu cross-checks; Java against android-34. Windows, Android and Linux bridges are compile-checked only. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
44 lines
2.1 KiB
TOML
44 lines
2.1 KiB
TOML
[package]
|
|
name = "makepad-widgets"
|
|
version = "2.0.0"
|
|
authors = ["Makepad <info@makepad.nl>"]
|
|
edition = "2021"
|
|
description = "Makepad widgets2"
|
|
license = "MIT OR Apache-2.0"
|
|
homepage = "https://github.com/makepad/makepad/"
|
|
repository = "https://github.com/makepad/makepad/"
|
|
metadata.makepad-auto-version = "N0YGjn7dnhc4DEHmww9lwuYwMVI="
|
|
|
|
[dependencies]
|
|
makepad-draw = { path = "../draw", version = "2.0.0" }
|
|
|
|
makepad-derive-widget = {path = "./derive_widget", version="2.0.0"}
|
|
makepad-mbtile-reader = { path = "../libs/mbtile_reader", version = "1.0.0", optional = true }
|
|
i_overlay = { path = "../libs/i_overlay", version = "7.0.3", optional = true, default-features = false }
|
|
makepad-fast-inflate = { path = "../libs/fast_inflate", optional = true }
|
|
# Silero VAD (the speech gate) from the speech model family; only that module.
|
|
makepad-ai-speech = { path = "../libs/ai/models/speech", default-features = false, features = ["vad"], optional = true }
|
|
# Speech-to-text sessions (Whisper here / machine / LAN, else the OS engine).
|
|
# No default features: only the speech pipes, never the image/video backends.
|
|
makepad-ai-hub = { path = "../libs/ai/hub", default-features = false, features = ["stt"], optional = true }
|
|
makepad-cef = { path = "../libs/cef", optional = true }
|
|
|
|
makepad-html = { path = "../libs/html", version = "1.0.0" }
|
|
unicode-segmentation = { version = "1.12.0", path = "../libs/unicode/unicode-segmentation" }
|
|
pulldown-cmark = { version = "0.12.2", path = "../libs/pulldown-cmark", default-features = false, features = ["simd"] }
|
|
makepad-latex-math = { path = "../libs/latex_math", version = "0.1.0" }
|
|
makepad-pdf-parse = { path = "../libs/pdf_parse", version = "1.0.0", optional = true }
|
|
ttf-parser = { path = "../libs/ttf-parser" }
|
|
|
|
serde = { version = "1.0", optional = true, features = ["derive"] }
|
|
|
|
[features]
|
|
default = []
|
|
|
|
voice = ["dep:makepad-ai-speech", "dep:makepad-ai-hub"]
|
|
maps = ["dep:makepad-mbtile-reader", "dep:makepad-fast-inflate", "dep:i_overlay"]
|
|
pdf = ["dep:makepad-pdf-parse"]
|
|
cef = ["dep:makepad-cef"]
|
|
|
|
## Enables certain public-facing types to derive serde serialization traits.
|
|
serde = ["dep:serde", "makepad-draw/serde", "makepad-derive-widget/serde"]
|