Labyricorn/voicebox
1
0
Fork 0
mirror of https://github.com/jamiepine/voicebox.git synced 2026-09-18 22:30:40 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat(capture): dictation, personalities, 0.5.0

Browse Source 
Ships the Capture release end to end. Global-hotkey dictation with
synthetic paste into the focused app on macOS and Windows, an on-screen
pill across recording / transcribing / refining, customizable push-to-
talk and toggle chords, and an accessibility-permission prompt scoped to
Settings → Captures with inline re-check feedback.

Voice profiles gain optional personalities that power compose / rewrite /
respond actions via a local Qwen3 LLM — shared with refinement, so there
is one local LLM in the app, not two.

Refinement hardened with deterministic Whisper-loop collapse before the
LLM sees the transcript, per-capture flag snapshots for re-runs, and a
ten-transcript evaluation harness across every bundled refinement size.

Version bump 0.4.5 → 0.5.0.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
This commit is contained in:
James Pine
2026-04-22 18:49:16 -07:00
co-authored by Claude Opus 4.7
parent ed2eec591a
commit 87c582ad54
84 changed files with 11043 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/database/migrations.py
+44
View File
@@ -34,6 +34,7 @@ def run_migrations(engine) -> None:
_migrate_generations(engine, inspector, tables)
_migrate_effect_presets(engine, inspector, tables)
_migrate_generation_versions(engine, inspector, tables)
_migrate_capture_settings(engine, inspector, tables)
_normalize_storage_paths(engine, tables)
@@ -146,6 +147,8 @@ def _migrate_profiles(engine, inspector, tables: set[str]) -> None:
_add_column(engine, "profiles", "design_prompt TEXT", "design_prompt")
if "default_engine" not in columns:
_add_column(engine, "profiles", "default_engine VARCHAR", "default_engine")
if "personality" not in columns:
_add_column(engine, "profiles", "personality TEXT", "personality")
def _migrate_generations(engine, inspector, tables: set[str]) -> None:
@@ -164,6 +167,13 @@ def _migrate_generations(engine, inspector, tables: set[str]) -> None:
_add_column(engine, "generations", "model_size VARCHAR", "model_size")
if "is_favorited" not in columns:
_add_column(engine, "generations", "is_favorited BOOLEAN DEFAULT 0", "is_favorited")
if "source" not in columns:
_add_column(
engine,
"generations",
"source VARCHAR NOT NULL DEFAULT 'manual'",
"source",
)
def _migrate_effect_presets(engine, inspector, tables: set[str]) -> None:
@@ -182,6 +192,40 @@ def _migrate_generation_versions(engine, inspector, tables: set[str]) -> None:
_add_column(engine, "generation_versions", "source_version_id VARCHAR", "source_version_id")
def _migrate_capture_settings(engine, inspector, tables: set[str]) -> None:
if "capture_settings" not in tables:
return
columns = _get_columns(inspector, "capture_settings")
if "allow_auto_paste" not in columns:
_add_column(
engine,
"capture_settings",
"allow_auto_paste BOOLEAN NOT NULL DEFAULT 1",
"allow_auto_paste",
)
if "default_playback_voice_id" not in columns:
_add_column(
engine,
"capture_settings",
"default_playback_voice_id VARCHAR",
"default_playback_voice_id",
)
if "chord_push_to_talk_keys" not in columns:
_add_column(
engine,
"capture_settings",
"chord_push_to_talk_keys TEXT NOT NULL DEFAULT '[\"MetaRight\",\"AltGr\"]'",
"chord_push_to_talk_keys",
)
if "chord_toggle_to_talk_keys" not in columns:
_add_column(
engine,
"capture_settings",
"chord_toggle_to_talk_keys TEXT NOT NULL DEFAULT '[\"MetaRight\",\"AltGr\",\"Space\"]'",
"chord_toggle_to_talk_keys",
)
def _normalize_storage_paths(engine, tables: set[str]) -> None:
"""Normalize stored file paths to be relative to the configured data dir."""
from pathlib import Path