Audio Hub › Voice assistants

MOSS-Speech

MOSS-Speech is a true speech-to-speech large language model without text guidance.

Category

Voice assistants

Type

Open source

Platform

Python project

Pricing

Free / open source

License

Apache-2.0

GitHub stars

139

Last updated

2026-02-13

GitHub repo → · Website →

Need the recording as text?

Whatever you record or edit with MOSS-Speech, Whipscribe turns it into an accurate, speaker-labeled transcript — 100+ languages, SRT/VTT/DOCX export, private self-hosted Whisper. About $2 per audio hour, 30 minutes free daily.

Transcribe a file →

Top MOSS-Speech alternatives

agenticSeekFully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of pipecatOpen Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.py-xiaozhiOpen-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.jarvisOffline voice assistant that respects your privacy. Forged in Rust. WIP.moltisA secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, CyberVerseSelf hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digit

See the full list of MOSS-Speech alternatives →