whereismyai
Astrbot Plugin Feiyu Voice
Astrbot Plugin Feiyu Voice: Audio plugin and local HTTP service providing voice synthesis, voice conversion, and singing generation.
Astrbot Plugin Feiyu Voice provides a local HTTP service and bot plugin for Feiyu TTS, RVC voice conversion, and optional score singing. It features two voice styles named cute and gentle, using the Fun-CosyVoice3-0.5B-2512 model and RVC v2. Users can convert clean vocals, generate speech from text, or produce singing using MIDI or ABC notation with SoulX-Singer. The service includes FastAPI integration, persistent task records, and Bearer authentication, with options for CUDA, ROCm, and Intel XPU hardware environments. It connects with AstrBot, DeepSeek, DSH, and other bots through unified API requests.
Astrbot Plugin Feiyu Voice at a glance
Key features
- Text-to-speech with cute and gentle voice styles
- RVC voice conversion for clean vocals
- Score singing generation using MIDI or ABC notation
- Song separation and mixing using external tools
- FastAPI backend with persistent task records
- Bearer authentication and asynchronous tasks
- Command-line and natural language tool calls
Use it for
- Generate cute or gentle spoken voice from text
- Convert clean vocals to Feiyu voice using RVC
- Create singing voices from MIDI or ABC notation
- Isolate vocals and mix complete songs with accompaniment
Alternatives to Astrbot Plugin Feiyu Voice
- AssemblyAI — Industry-leading speech models deliver high accuracy and low latency for voice applications.
- Kokoro-FastAPI — Generate hours of high quality speech with an OpenAI-compatible endpoint.
- FireRedTTS3 — It offers zero-shot voice cloning across 24 languages and 21 Chinese dialects.
- TTS WebUI — It offers a free web interface with over 30 AI models for audio generation.
- Pipecat — Builds real-time voice and multimodal agents with frame-level control.
- Willow — Fast, private, open source voice control using local hardware.
- kokoro-onnx — Runs local TTS inference with efficient ONNX runtime performance.
- Free ASR — Zero-dependency real-time streaming speech-to-text with no account login required.
- Moonshine — Runs entirely in your browser with no audio leaving your device.
- Superwhisper — Transcribes speech offline and online with custom AI modes and templates.
- Speaches — It acts as an Ollama equivalent for running local TTS and STT models.
- PaddleSpeech — It offers state-of-the-art models and streaming systems for speech tasks.
All Astrbot Plugin Feiyu Voice alternatives