69aa35a51c
Major feature additions inspired by OpenClaw/ClawdBot integration analysis: Voice Message Transcription (STT): - Auto-transcribe voice/audio messages via OpenAI Whisper API - Download voice to ~/.hermes/audio_cache/ on Telegram/Discord/WhatsApp - Inject transcript as text so all models can understand voice input - Configurable model (whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe) Telegram Sticker Understanding: - Describe static stickers via vision tool with JSON-backed cache - Cache keyed by file_unique_id avoids redundant API calls - Animated/video stickers get emoji-based fallback description Discord Rich UX: - Native slash commands (/ask, /reset, /status, /stop) via app_commands - Button-based exec approvals (Allow Once / Always Allow / Deny) - ExecApprovalView with user authorization and timeout handling Slack Integration: - Full SlackAdapter using slack-bolt with Socket Mode - DMs, channel messages (mention-gated), /hermes slash command - File attachment handling with bot-token-authenticated downloads DM Pairing System: - Code-based user authorization as alternative to static allowlists - 8-char codes from unambiguous alphabet, 1-hour expiry - Rate limiting, lockout after failed attempts, chmod 0600 on data - CLI: hermes pairing list/approve/revoke/clear-pending Event Hook System: - File-based hook discovery from ~/.hermes/hooks/ - HOOK.yaml + handler.py per hook, sync/async handler support - Events: gateway:startup, session:start/reset, agent:start/step/end - Wildcard matching (command:* catches all command events) Cross-Channel Messaging: - send_message agent tool for delivering to any connected platform - Enables cron job delivery and cross-platform notifications Human-Like Response Pacing: - Configurable delays between message chunks (off/natural/custom) - HERMES_HUMAN_DELAY_MODE env var with min/max ms settings Warm Injection Message Style: - Retrofitted image vision messages with friendly kawaii-consistent tone - All new injection messages (STT, stickers, errors) use warm style Also: updated config migration to prompt for optional keys interactively, bumped config version, updated README, AGENTS.md, .env.example, cli-config.yaml.example, install scripts, pyproject.toml, and toolsets.
104 lines
3.0 KiB
Python
104 lines
3.0 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Transcription Tools Module
|
|
|
|
Provides speech-to-text transcription using OpenAI's Whisper API.
|
|
Used by the messaging gateway to automatically transcribe voice messages
|
|
sent by users on Telegram, Discord, WhatsApp, and Slack.
|
|
|
|
Supported models:
|
|
- whisper-1 (cheapest, good quality)
|
|
- gpt-4o-mini-transcribe (better quality, higher cost)
|
|
- gpt-4o-transcribe (best quality, highest cost)
|
|
|
|
Supported input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg
|
|
|
|
Usage:
|
|
from tools.transcription_tools import transcribe_audio
|
|
|
|
result = transcribe_audio("/path/to/audio.ogg")
|
|
if result["success"]:
|
|
print(result["transcript"])
|
|
"""
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Optional
|
|
|
|
|
|
# Default STT model -- cheapest and widely available
|
|
DEFAULT_STT_MODEL = "whisper-1"
|
|
|
|
|
|
def transcribe_audio(file_path: str, model: Optional[str] = None) -> dict:
|
|
"""
|
|
Transcribe an audio file using OpenAI's Whisper API.
|
|
|
|
This function calls the OpenAI Audio Transcriptions endpoint directly
|
|
(not via OpenRouter, since Whisper isn't available there).
|
|
|
|
Args:
|
|
file_path: Absolute path to the audio file to transcribe.
|
|
model: Whisper model to use. Defaults to config or "whisper-1".
|
|
|
|
Returns:
|
|
dict with keys:
|
|
- "success" (bool): Whether transcription succeeded
|
|
- "transcript" (str): The transcribed text (empty on failure)
|
|
- "error" (str, optional): Error message if success is False
|
|
"""
|
|
api_key = os.getenv("OPENAI_API_KEY")
|
|
if not api_key:
|
|
return {
|
|
"success": False,
|
|
"transcript": "",
|
|
"error": "OPENAI_API_KEY not set",
|
|
}
|
|
|
|
audio_path = Path(file_path)
|
|
if not audio_path.is_file():
|
|
return {
|
|
"success": False,
|
|
"transcript": "",
|
|
"error": f"Audio file not found: {file_path}",
|
|
}
|
|
|
|
# Use provided model, or fall back to default
|
|
if model is None:
|
|
model = DEFAULT_STT_MODEL
|
|
|
|
try:
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(api_key=api_key)
|
|
|
|
with open(file_path, "rb") as audio_file:
|
|
transcription = client.audio.transcriptions.create(
|
|
model=model,
|
|
file=audio_file,
|
|
response_format="text",
|
|
)
|
|
|
|
# The response is a plain string when response_format="text"
|
|
transcript_text = str(transcription).strip()
|
|
|
|
print(f"[STT] Transcribed {audio_path.name} ({len(transcript_text)} chars)", flush=True)
|
|
|
|
return {
|
|
"success": True,
|
|
"transcript": transcript_text,
|
|
}
|
|
|
|
except Exception as e:
|
|
print(f"[STT] Transcription error: {e}", flush=True)
|
|
return {
|
|
"success": False,
|
|
"transcript": "",
|
|
"error": str(e),
|
|
}
|
|
|
|
|
|
def check_stt_requirements() -> bool:
|
|
"""Check if OpenAI API key is available for speech-to-text."""
|
|
return bool(os.getenv("OPENAI_API_KEY"))
|