VoiceOpen source

Moshi

Open speech-text foundation model for full-duplex spoken dialogue.

About the tool

Open speech-text foundation model for full-duplex spoken dialogue.

Moshi, from Kyutai, is a speech-to-speech foundation model and dialogue framework that supports full-duplex conversation using the Mimi streaming neural audio codec. Code is released under MIT and Apache-2.0 licenses with CC-BY 4.0 model weights, making it a reference open stack for realtime speech-native agents.

Pricing: Open source
Category: Voice
Maker: Not publicly supplied
Provenance: Indexed by Attest from public information

Backlink artifact

Show the Attested badge.

This badge links to the public evidence record. The link is followed; the verification claim remains limited to the checks shown above.

Embed HTML

<a href="https://getattest.com.au/t/moshi"><img src="https://getattest.com.au/badge/moshi" alt="Attested — verified by Attest"></a>

Same category

Similar verified tools.

✓ Attested

VoiceFreemium

Fish Audio

Text-to-speech and voice cloning platform built on the open Fish Speech models.

Verified 25 Aug 2026 · Indexed by Attest

✓ Attested

VoiceOpen source

Coqui TTS

Open-source deep learning toolkit for text-to-speech.

Verified 25 Aug 2026 · Indexed by Attest

✓ Attested

VoiceOpen source

Kokoro

Open-weight 82M-parameter text-to-speech model with fast inference.

Verified 25 Aug 2026 · Indexed by Attest