AbstractVoice

# Base install (remote OpenAI-compatible TTS/STT)
pip install abstractvoice

# Full local stack for macOS Apple Silicon
pip install "abstractvoice[apple]"

# Full local stack for GPU (Linux/Windows)
pip install "abstractvoice[gpu]"

# Granular extras
pip install "abstractvoice[supertonic,stt,audio-io]"

# Download local TTS models
abstractvoice-prefetch --supertonic
abstractvoice-prefetch --piper en

# Download local STT model
abstractvoice-prefetch --stt small

# Optional cloning backends
abstractvoice-prefetch --omnivoice
abstractvoice-prefetch --openf5

from abstractvoice import VoiceManager

# Remote TTS (reads OPENAI_API_KEY from env)
vm = VoiceManager(language="en")
vm.speak("Hello from AbstractVoice.")

# Get WAV bytes for headless usage
wav = vm.speak_to_bytes("Headless TTS output.", format="wav")

# Fully local TTS + STT
vm_local = VoiceManager(
    language="en",
    tts_engine="supertonic",
    stt_engine="faster_whisper",
)
vm_local.speak("Running entirely offline.")

# Interactive REPL (remote by default)
abstractvoice --verbose

# Fully local REPL
abstractvoice --tts-engine supertonic --stt-engine faster_whisper --verbose

# Local web UI (requires abstractvoice[web])
abstractvoice web --port 5000

from abstractvoice import VoiceManager

vm = VoiceManager(
    language="en",
    tts_engine="openai",       # or "supertonic", "piper", "omnivoice"
    stt_engine="openai",       # or "faster_whisper"
    remote_base_url="...",    # optional OpenAI-compatible endpoint
)

# TTS
vm.speak("Hello world")
wav = vm.speak_to_bytes("Hello", format="wav")

# Engine preload/unload (local engines only)
vm.preload_tts_engine(engine="supertonic")
vm.preload_stt_engine(engine="faster_whisper")
vm.unload_tts_engine()
vm.unload_stt_engine()

# Runtime TTS switching
vm.set_tts_engine("piper")

from abstractcore import create_llm

llm = create_llm("openai")

# TTS via capability plugin
wav = llm.voice.tts(
    "Hello from AbstractCore",
    provider="openai",
    model="tts-1",
    voice="alloy",
    format="wav",
)

# STT via capability plugin
text = llm.voice.stt(audio_bytes, provider="faster-whisper", model="small")

# Provider and voice discovery
providers = llm.voice.available_providers()
voices = llm.voice.list_tts_voices(provider="supertonic")
models = llm.voice.list_tts_models(provider="openai")

# Voice cloning
llm.voice.clone_voice(reference_audio="ref.wav", name="my-clone")

# Resident model management (local engines)
llm.voice.load_resident_model(provider="supertonic")
llm.voice.list_resident_models()
llm.voice.unload_resident_model(provider="supertonic")

from abstractvoice.tts.text_to_speech_stream import TextToSpeechStream

# Bridge incremental LLM text to TTS audio
stream = TextToSpeechStream(tts_engine=vm.tts_engine)

# Feed tokens as they arrive from the LLM
for token in llm_stream:
    stream.feed(token)
stream.finish()