Self-hosted alternatives to Unmute by Kyutai
200 self-hosted apps like Unmute by Kyutai, closest match first.
Top picks
- V
Voice Chat AI
Launch🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses SparkTTS, OpenAI, ElevenLabs, Kokoro, xAI and more
FreeOpen sourceSelf-hosted
- O
OpenClaw Voice
LaunchTalk to your AI assistant like Alexa. Self-hosted, private, open-source. Browser-based voice conversations with Whisper STT and ElevenLabs TTS. Works with OpenAI, Claude, and custom agents.
FreeOpen sourceSelf-hosted
- C
Chatterbox TTS API
LaunchLocal, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.) with multilingual support.
FreeOpen sourceSelf-hosted
- K
Kokoro Web
Launch🔊 Kokoro Web: Free AI text-to-speech, online or self-hosted, OpenAI compatible!
FreeOpen sourceSelf-hosted
- C
Chatterbox-TTS-Server
LaunchSelf-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDI
FreeOpen sourceSelf-hosted
- D

Diction
LaunchDiction is a keyboard for iPhone with one-tap dictation and writing tools built in. The microphone sits above the keys in every app, so you can speak a message and send it without typing. Speech recognition runs in one of three modes: on th
FreeOpen sourceSelf-hosted
More like Unmute by Kyutai
AI Avatar System
🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk…
About Unmute by Kyutai
Unmute by Kyutai
Make LLMs listen and speak
Unmute is a demo from Kyutai for speaking with an AI model by voice. It makes an LLM listen and speak, using low-latency open-source speech-to-text and text-to-speech. You pick a character from the list, such as Watercooler, Quiz show, Gertrude, Dev news, Explanation, Charles, Developpeuse or Fabieng, then connect to start the conversation. You can add instructions for the character before you connect, and you can download a recording of the session. The page asks for consent before recording the transcript of your conversation, and it says your voice will not be stored, which helps the non-profit's research. Kyutai also points to Pocket TTS, a tiny text-to-speech model with voice cloning, as a newer release. The page includes cookie choices, and you can decline non-essential cookies.
- Category
- AI
- Website
- unmute.sh


