adolforeyna/VoiceAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • d8c44cf92d refactor: replace Qwen 1.7B with Qwen3-TTS 0.6B as default Qwen TTS engine main Adolfo Reyna 2026-08-13 22:55:37 -04:00
  • bcd6cfb500 perf: switch QwenTTSService to Qwen3-TTS 0.6B for 3x faster generation and lower memory Adolfo Reyna 2026-08-13 22:54:04 -04:00
  • c95d738f88 feat: add QwenTTSService for MLX Qwen3-TTS 1.7B integration Adolfo Reyna 2026-08-13 22:39:56 -04:00
  • 70da5d857a feat: integrate JV Voice Profile cloning, Voicebox research, and ensure session voice/markdown prompt nudge Adolfo Reyna 2026-08-12 19:57:03 -04:00
  • 811a40f2cc fix: isolate reasoning chunks from assistant spoken reply history and Web UI final reply Adolfo Reyna 2026-08-12 10:38:23 -04:00
  • fc9397cd85 fix: fuzzy normalization and set_voice method for dynamic inline voice switching Adolfo Reyna 2026-08-12 10:26:06 -04:00
  • 404a7071fb feat: real-time reasoning speech, dynamic voice tags, and unified web UI bubbles Adolfo Reyna 2026-08-12 10:17:47 -04:00
  • b5034b4b16 Preserve macOS app permissions via dynamic launcher, .env workspace path, and session/audio tools Adolfo Reyna 2026-08-11 21:15:37 -04:00
  • 583131221c Add AGENTS.md documenting project architecture, Hermes integration learnings, and build steps Adolfo Reyna 2026-08-09 22:53:51 -04:00
  • 84e20f8d81 Apply Hermes optimizations: per-workspace session state file, silent spoken tool activity, clean single-frame turn termination Adolfo Reyna 2026-08-09 21:46:12 -04:00
  • 2f181ff4f1 Replace OpenCode harness with Hermes, remove workspace dependency, and move vocabulary/corrections to app folder Adolfo Reyna 2026-08-09 21:35:52 -04:00
  • 6e8a578e86 Add macOS app bundle packaging, native launcher, and MACOS_APP_PACKAGING guide Adolfo Reyna 2026-08-08 17:37:52 -04:00
  • 757261ebfd Enable live real-time TTS voice synchronization between VoiceManager and KokoroTTS Adolfo Reyna 2026-08-07 20:23:21 -04:00
  • 469d372338 Make voice_tool dependency-free and add voice alias mappings for macOS vs Kokoro names Adolfo Reyna 2026-08-07 20:20:36 -04:00
  • 5b1aad3fa3 Auto-install bin/voice_tool.py into working workspace directory Adolfo Reyna 2026-08-07 20:18:33 -04:00
  • 351b87beb8 Add voice management tool bin/voice_tool.py and dynamic voice switching system Adolfo Reyna 2026-08-07 20:16:35 -04:00
  • 87b54ce8f4 Aggregate turn text into a complete LLMTextFrame to prevent TTS sentence truncation Adolfo Reyna 2026-08-07 20:14:38 -04:00
  • ba16e9ca27 Fix speech text truncation bug where Assistant: prefix caused multi-line responses to drop remaining sentences Adolfo Reyna 2026-08-07 20:04:34 -04:00
  • af15e64e0a Restore live tool execution logging in console for OpenCode Adolfo Reyna 2026-08-07 19:47:05 -04:00
  • 0aa790a8b0 Fix OpenCode server HTTP response parsing for parts array Adolfo Reyna 2026-08-07 19:43:03 -04:00
  • a8ad741a4d Implement OpenCode server daemon integration with automatic fallback to CLI Adolfo Reyna 2026-08-07 19:41:07 -04:00
  • 116e2e3763 Enable session persistence with --continue and instruct model to complete tool loops fully Adolfo Reyna 2026-08-07 19:36:36 -04:00
  • f0be1a8cdf Log OpenCode tool execution steps in real time in voice assistant console Adolfo Reyna 2026-08-07 19:32:25 -04:00
  • 1386615c49 Enable OpenCode tools with --auto in opencode_llm.py Adolfo Reyna 2026-08-07 19:28:40 -04:00
  • 7173300298 Add strict truthfulness instruction to VOICE_STYLE to prevent hallucinated tool execution Adolfo Reyna 2026-08-07 19:27:35 -04:00
  • b510cedbf8 Set default working directory for OpenCode to ~/Workspace Adolfo Reyna 2026-08-07 19:13:34 -04:00
  • 40a4107bc9 Integrate OpenCode CLI with ollama-cloud/gemma4:31b Adolfo Reyna 2026-08-07 19:10:32 -04:00
  • 4773b93779 Add OpenCode / Ollama LLM integration with gemma4:31b default Adolfo Reyna 2026-08-07 18:57:11 -04:00
  • 1a8a93695b Set Qwen2.5-7B-Instruct-4bit as default MLX model and add spoken text filtering Adolfo Reyna 2026-08-07 18:46:05 -04:00
  • 3fad171905 Fix Gemma chat template system prompt compatibility in apple_llm.py Adolfo Reyna 2026-08-07 18:37:07 -04:00
  • c50da6f29c Set Gemma 2 2B MLX as default local model and add --mlx-model flag Adolfo Reyna 2026-08-07 18:32:57 -04:00
  • 24d6e436a0 Update LLMHelper diagnostic reporting and swiftc target version Adolfo Reyna 2026-08-07 18:29:15 -04:00
  • f579a26cc0 Add AGENTS.md template and fix repetition penalty for local macOS LLM Adolfo Reyna 2026-08-07 18:27:51 -04:00
  • 598d55e383 Add macOS LLM model engine support and environment setup Adolfo Reyna 2026-08-07 18:23:38 -04:00
  • 62d805e565 Initial commit of current state Adolfo Reyna 2026-08-07 18:15:36 -04:00