josedario87 ac17a9f292 fix: Improve Whisper transcription with WebM to WAV conversion ...

- Add ffmpeg conversion from WebM/Opus to WAV (16kHz mono PCM)
- Optimize transcription parameters (VAD, temperature, beam_size)
- Add Honduras Spanish context prompt with local expressions
- Fix chunk accumulation display in voice panel
- Add 1.5s recording buffer after releasing Ctrl+Space
- Skip small audio chunks (<5KB) that cause ffmpeg errors
- Use large-v3 model for better accuracy

2026-02-14 00:16:01 -06:00

..

db

refactor: Modularize server into separate concerns

2026-02-13 13:01:18 -06:00

routes

feat: Add Whisper GPU speech-to-text with progressive transcription

2026-02-13 23:47:52 -06:00

services

feat: Add Whisper GPU speech-to-text with progressive transcription

2026-02-13 23:47:52 -06:00

utils

refactor: Modularize server into separate concerns

2026-02-13 13:01:18 -06:00

agent-ui.db

feat: Add dynamic MCP tool registration per page

2026-02-13 05:42:17 -06:00

bun.lock

feat: Redesign FloatingTerminal with Windows Vista Aero style

2026-02-13 18:27:17 -06:00

config.ts

refactor: Modularize server into separate concerns

2026-02-13 13:01:18 -06:00

index.ts

feat: Add Whisper GPU speech-to-text with progressive transcription

2026-02-13 23:47:52 -06:00

package-lock.json

feat: Redesign FloatingTerminal with Windows Vista Aero style

2026-02-13 18:27:17 -06:00

package.json

feat: Add WebMCP token polling for automatic browser connection

2026-02-13 07:49:15 -06:00

terminal.ts

feat: Add Whisper GPU speech-to-text with progressive transcription

2026-02-13 23:47:52 -06:00

whisper_server.py

fix: Improve Whisper transcription with WebM to WAV conversion

2026-02-14 00:16:01 -06:00