Add Text-to-Speech (TTS) functionality with multiple providers

Add tool previews

Add AGENTS and SOUL.md support

Add Exec Approval
This commit is contained in:
teknium1 2026-02-12 10:05:08 -08:00
parent 89c6f24d48
commit f5be6177b2
18 changed files with 1200 additions and 21 deletions

View file

@ -99,6 +99,24 @@ DEFAULT_CONFIG = {
"personality": "kawaii",
},
# Text-to-speech configuration
"tts": {
"provider": "edge", # "edge" (free) | "elevenlabs" (premium) | "openai"
"edge": {
"voice": "en-US-AriaNeural",
# Popular: AriaNeural, JennyNeural, AndrewNeural, BrianNeural, SoniaNeural
},
"elevenlabs": {
"voice_id": "pNInz6obpgDQGcFmaJgB", # Adam
"model_id": "eleven_multilingual_v2",
},
"openai": {
"model": "gpt-4o-mini-tts",
"voice": "alloy",
# Voices: alloy, echo, fable, onyx, nova, shimmer
},
},
# Permanently allowed dangerous command patterns (added via "always" approval)
"command_allowlist": [],
@ -202,6 +220,13 @@ OPTIONAL_ENV_VARS = {
"url": None,
"password": False,
},
# Text-to-speech (premium providers)
"ELEVENLABS_API_KEY": {
"description": "ElevenLabs API key for premium text-to-speech voices",
"prompt": "ElevenLabs API key",
"url": "https://elevenlabs.io/",
"password": True,
},
# Terminal configuration
"MESSAGING_CWD": {
"description": "Working directory for terminal commands via messaging (Telegram/Discord/etc). CLI always uses current directory.",

View file

@ -186,6 +186,11 @@ def _print_setup_summary(config: dict, hermes_home):
else:
tool_status.append(("Image Generation", False, "FAL_KEY"))
# TTS (always available via Edge TTS; ElevenLabs/OpenAI are optional)
tool_status.append(("Text-to-Speech (Edge TTS)", True, None))
if get_env_value('ELEVENLABS_API_KEY'):
tool_status.append(("Text-to-Speech (ElevenLabs)", True, None))
# Tinker + WandB (RL training)
if get_env_value('TINKER_API_KEY') and get_env_value('WANDB_API_KEY'):
tool_status.append(("RL Training (Tinker)", True, None))
@ -991,6 +996,28 @@ def run_setup_wizard(args):
print_success(" Configured ✓")
print()
# ElevenLabs - Premium TTS
print_info("" * 50)
print(color(" Text-to-Speech - ElevenLabs (Premium)", Colors.CYAN))
print_info(" Enables: Premium TTS voices (Edge TTS is free and works without a key)")
print_info(" Use case: High-quality, customizable voice synthesis")
if get_env_value('ELEVENLABS_API_KEY'):
print_success(" Status: Configured ✓")
if prompt_yes_no(" Update ElevenLabs API key?", False):
api_key = prompt(" API key", password=True)
if api_key:
save_env_value("ELEVENLABS_API_KEY", api_key)
print_success(" Updated")
else:
print_warning(" Status: Not configured (free Edge TTS will be used by default)")
if prompt_yes_no(" Set up ElevenLabs?", False):
print_info(" Get your API key at: https://elevenlabs.io/")
api_key = prompt(" API key", password=True)
if api_key:
save_env_value("ELEVENLABS_API_KEY", api_key)
print_success(" Configured ✓")
print()
# Tinker + WandB - RL Training
print_info("" * 50)
print(color(" RL Training (Tinker + WandB)", Colors.CYAN))

View file

@ -76,6 +76,7 @@ def show_status(args):
"FAL": "FAL_KEY",
"Tinker": "TINKER_API_KEY",
"WandB": "WANDB_API_KEY",
"ElevenLabs": "ELEVENLABS_API_KEY",
}
for name, env_var in keys.items():