Build integrated IS/BS/CF financial workbooks in Excel.
The English summary is being prepared. Showing the original description.
Use for the Windows TTS+STT voice interface in OpenAmer.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Ein reines Python-Standardbibliothek Voice-Interface für OpenAmer auf Windows. Nutzt PowerShell System.Speech für Text-to-Speech (TTS) und Speech-to-Text (STT, Windows Diktat-API via DictationGrammar).
Datei: scripts/voice-assistant.py im OpenAmer-Home ($OPENAMER_HOME/scripts/)
| Flag | Beschreibung |
|---|---|
--listen | Nimmt Mikrofon auf (10s Standard-Timeout), gibt erkannten Text auf stdout aus. |
--speak 'Text' | Gibt Text per PowerShell TTS aus (System.Speech). |
--chat | Interaktiver Chat: sprich oder tippe, erhalte TTS-Antwort (Echo-Demo). |
--list-voices | Listet installierte Windows-TTS-Stimmen. |
--log N | Zeigt Konversations-Log der letzten N Tage. |
--voice 'Name' | Wählt eine bestimmte TTS-Stimme (z. B. 'Microsoft Zira Desktop'). |
0 – Erfolg1 – Mikrofon/STT nicht verfügbar (kein Mikrofon, keine Sprache)2 – TTS-FehlerAlle Sitzungen werden als JSONL in ~/.voice-assistant/conversations/ geloggt.
Dateinamen: conversation_YYYYMMDD_HH.jsonl (stündlich rotiert).
Einträge enthalten: session_id, turn, role, text, timestamp, mode (speech|text).
cd "$OPENAMER_HOME/scripts"
python voice-assistant.py --list-voices
python voice-assistant.py --speak 'Hallo Welt'
python voice-assistant.py --listen --timeout 5
python voice-assistant.py --chat
| Problem | Ursache | Lösung |
|---|---|---|
SpeechRecognitionEngine nicht verfügbar | Windows Speech Recognition deaktiviert | Systemsteuerung > Spracherkennung aktivieren |
Add-Type … System.Speech schlägt fehl | .NET Framework 3.5 fehlt | dism /online /Enable-Feature /FeatureName:NetFx3 |
| Keine TTS zu hören | Standard-Lautsprecher falsch | Windows Audio-Einstellungen prüfen |
| STT timeout | Kein Mikrofon oder keine Sprache | Mikrofon-Eingabe prüfen, --timeout 15 versuchen |
--speak mit Sonderzeichen | Escaping in PowerShell | Text in einfache Anführungszeichen setzen |
Der Voice-Assistent kann aus anderen Skills/OA-Scripts importiert werden:
import sys
sys.path.insert(0, r'$OPENAMER_HOME\scripts')
from voice_assistant import tts_powershell, stt_listen, log_conversation
┌─────────────────────┐ subprocess ┌───────────────────────────┐
│ voice-assistant.py │ ──────────────────> │ PowerShell │
│ (Python, stdlib) │ │ - System.Speech.Synthesis│
│ │ <────────────────── │ - System.Speech.Recog. │
│ CLI argparse │ stdout/stderr └───────────────────────────┘
│ Session-Log (JSONL) │
│ ~/.voice-assistant/ │
└─────────────────────┘
windows-compatibility, windows-computer-use
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Build integrated IS/BS/CF financial workbooks in Excel.
The English summary is being prepared. Showing the original description.
Run and grow the OpenAmer Agent-to-Agent swarm: identity, trust, node-to-node ask, signed skill/insight sharing, and the autonomous self-learning loop.
The English summary is being prepared. Showing the original description.
Use for A/B experiments on OpenAmer configs and skills.
The English summary is being prepared. Showing the original description.
Roleplay a hostile user to find and triage UX pain points.
The English summary is being prepared. Showing the original description.
Agent mesh: master/worker nodes, HTTP delegation, heartbeat.
The English summary is being prepared. Showing the original description.
Use for agentic commerce payments tasks. Candidate synthesized from trend radar; awaiting trial promotion.
The English summary is being prepared. Showing the original description.