VoiceMem:面向实时语音智能体的记忆系统

git clone https://github.com/xzf-thu/VoiceMem.git
cd VoiceMem

# Install the memory system (bundles ASR / speaker ID / scene / emotion / local embedding)
pip install voicemem

# Optional: run our fine-tuned Qwen reply model
pip install "voicemem[slm]"

pip install -U huggingface_hub

hf download zhifeixie/VoiceMem_Default_Models_Env --local-dir ./models

from voicemem import VoiceMem

vm = VoiceMem(
    mode="normal",
    openai_key="api_xxx",
    top_k=5,
)

# Local models load lazily -- warm them up so the first call doesn't pay for it.
vm.warmup()

# Store an audio file.
# VoiceMem internally runs ASR / speaker ID / scene / emotion / embedding extraction.
print("ingest start")
vm.ingest(audio="assets/input.wav")  # I am vegetarian and allergic to nuts.
print("ingest done")

# Writing is slow because it extracts facts, tags them and builds the graph.
# Reading is a pure vector lookup -- independent of write cost.
print("search start")
result = vm.search("What are my dietary restrictions?")
print("search done")

print(result.result_leftbrain, result.result_rightbrain)

# Store Left Brain factual text directly (no emotional information).
vm = VoiceMem(
    mode="leftbrain_only",
    openai_key="api_xxx",
    top_k=5,
)

vm.ingest("I am vegetarian and allergic to nuts.")

result = vm.search("What are my dietary restrictions?")

import asyncio
import os
from pprint import pprint

import numpy as np
import soundfile as sf

from voicemem import VoiceMem

# Reuses the vm above; building one here so the block runs standalone
vm = VoiceMem(mode="normal", openai_key=os.environ["OPENAI_API_KEY"], top_k=5)

# Local models load lazily -- warm them up so the first audio chunk doesn't wait
vm.warmup()

# Store one fact first, so the question below has something to find
vm.ingest("I am vegetarian and allergic to nuts.")

SPEC_MIN_CHARS = 6
searching = False

def on_partial(text):
    """Partial transcripts as they arrive. Long enough = the search already started."""
    global searching
    print(f"\r[partial] {text}", end="", flush=True)
    if not searching and len(text) >= SPEC_MIN_CHARS:
        searching = True
        print("\n[search start] speaker isn't done yet, retrieval already running", flush=True)

async def main():
    # This audio is a question: "What are my dietary restrictions?"
    audio, sr = sf.read("assets/question.wav", dtype="float32")
    pcm = (np.clip(audio, -1, 1) * 32767).astype(np.int16)

    stream = vm.stream(src_rate=sr, vad_threshold=0.5, on_partial=on_partial)
    step = int(sr * .032)

    for i in range(0, len(pcm), step):
        st = await stream.feed(pcm[i:i + step].tobytes())
        if st.state != "turn_over":
            continue

        # VAD confirmed end of turn. Memory was fetched while the user spoke -- just read it
        print("[search end]")
        print("transcript  ", st.transcript)
        print("left brain  ", st.result_leftbrain)
        print("right brain ", st.result_rightbrain)
        pprint({k: getattr(st, k) for k in
                ["speaker_id", "speaker_voiceprint", "emotion",
                 "entity", "schema", "text_embedding"]})

        # Every turn runs the ingest decision
        print("[ingest] LLM deciding whether this is worth storing...", flush=True)
        res = vm.ingest(st.transcript)
        print(f"[ingest] extracted {res['facts_count']} facts -> {res['memory_ids']}")

asyncio.run(main())

python web/run.py

http://localhost:8787