Skip to main content

AI-powered video call with virtual companions

Project description

Fancall Backend

AI 아이돌과 실시간 영상 통화 Python 패키지

주요 기능

  • LiveKit 기반 실시간 음성/영상 통화
  • Fish Audio TTS 음성 합성
  • Hedra 아바타 지원 (선택)
  • 동적 설정 (voice_id, avatar_id, system_prompt)

설치

cd backend
poetry install
poetry run uvicorn main:app --reload

API 문서:

LiveKit 설정

서버

brew install livekit
livekit-server --dev

서버: ws://localhost:7880 (API Key: devkey, Secret: secret)

Agent

cd backend
export OPENAI_API_KEY=sk-...
export FISH_API_KEY=...

# 개발 모드
python -m fancall.agent.worker dev

# 프로덕션 모드
python -m fancall.agent.worker start

# 특정 룸 연결
python -m fancall.agent.worker connect --room <room-name>

사용법

FastAPI 통합

from fancall.api.router import create_fancall_router
from fancall.factories import LiveRoomRepositoryFactory
from fancall.settings import LiveKitSettings

router = create_fancall_router(
    livekit_settings=LiveKitSettings(),
    jwt_settings=jwt_settings,
    db_session_factory=db_session_factory,
    repository_factory=LiveRoomRepositoryFactory(db_session_factory),
)
app.include_router(router, prefix="/api")

개발

poetry install
make lint
make type-check
make unit-test
make format

데이터베이스 마이그레이션

데이터베이스 스키마를 최신 상태로 업데이트하려면:

make migrate

새로운 마이그레이션을 생성하려면 (models.py 변경 후):

poetry run alembic revision --autogenerate -m "변경 설명"

환경 변수

필수 (Agent 실행 시)

변수 설명
OPENAI_API_KEY OpenAI API 키
FISH_API_KEY Fish Audio TTS API 키

선택 (기능 활성화)

변수 기본값 설명
FANCALL_OPENAI_MODEL gpt-4o-mini 사용할 OpenAI LLM 모델
HEDRA_ENABLED false Hedra 아바타 활성화
HEDRA_API_KEY - Hedra API 키 (enabled=true일 때 필수)

참고: LiveKit, 데이터베이스, 모델 등 추가 설정은 기본값으로 로컬 개발 가능합니다. 변경이 필요한 경우 fancall/settings.py의 Settings 클래스를 참고하세요.

의존성

  • aioia-core (공통 인프라)
  • FastAPI, SQLAlchemy, Pydantic
  • livekit-api, livekit-agents

라이선스

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fancall-0.3.0.tar.gz (14.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fancall-0.3.0-py3-none-any.whl (17.3 kB view details)

Uploaded Python 3

File details

Details for the file fancall-0.3.0.tar.gz.

File metadata

  • Download URL: fancall-0.3.0.tar.gz
  • Upload date:
  • Size: 14.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for fancall-0.3.0.tar.gz
Algorithm Hash digest
SHA256 c11c97bfd7142c593e4a134b894badc74441b4b6a37ed2c7d271573d0675266b
MD5 1e8e83c6e4450cc8573ab28fc1c0ea17
BLAKE2b-256 dbc4c294615744d86758fc9396ce1140b0b9367fd2bd781c51565781c3ab8468

See more details on using hashes here.

Provenance

The following attestation bundles were made for fancall-0.3.0.tar.gz:

Publisher: publish-backend.yml on algorima/fancall

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file fancall-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: fancall-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 17.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for fancall-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0c185a156eb8ef3c3f84347409284b843a2f61fb6f84d9e7db15ef5e21a28fa7
MD5 be1b663cba7acce578700358c07dba6b
BLAKE2b-256 c9207a01111edc1d93ad81307e2fb901839c06e1652dcecd86570492ebc60118

See more details on using hashes here.

Provenance

The following attestation bundles were made for fancall-0.3.0-py3-none-any.whl:

Publisher: publish-backend.yml on algorima/fancall

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page