Google Opens Lyria 3.5 to Developers, Generating Full Songs With Vocals
Google's newest music generation model expands from Flow Music into the Gemini API, AI Studio, and the Gemini app with 44.1 kHz stereo output.
// Intelligence
Audio
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
Microsoft's MAI-Transcribe-2 Beats ElevenLabs on Accuracy at 54% Lower Price
Microsoft AI's new speech recognition model hits 2.0% word error rate at 411x real time speed for $1.67 per 1,000 minutes.
audio.cpp Runs Speech and Music AI up to 5x Faster Without Python
A pure C++ inference engine built on ggml runs TTS, ASR, voice cloning, and music generation up to 5x faster than Python baselines with no Python dependency.
Meta's Muse Voice Transcribe Beats Every Rival With 3.1% Error Rate
Meta Superintelligence Labs' new real-time speech model tops streaming ASR and diarization benchmarks, handles 20+ speakers, and ships at $0.18 per hour.
Sesame's TurnBench Exposes How Gemini Live and OpenAI Realtime Fumble Conversations
Sesame releases an open benchmark that scores voice agents on when they speak, yield, or stay silent, exposing where every current system fails.
Sarvam Opens Content Studio to Dub Videos Into 11 Indian Languages
Sarvam opens its multilingual voice and video workspace to the public, bundling dubbing, cloning, and TTS across 11 Indian languages into one browser tool.
T8's MiniMax H3 ComfyUI Pack Runs 60-Second Video on 16 GB
A community developer shipped a 54-node ComfyUI extension for MiniMax H3 with same-day tooling for Alibaba PAI's new 8-step acceleration LoRAs.
Google's Gemini 3.5 Transcribe Hits 2.6% Error Rate and Reads Your Screen
Google's new speech-to-text model hits 2.6% word error rate, adds screen-aware context in Antigravity, and ships behind two developer APIs.
Fish Audio Squeezes 2M Voices and Voice Cloning Into an iPhone App
Fish Audio brings its full voice studio to iPhone with 2M+ voices, 80+ languages, and open-ended emotion tags. Here is what shipped.
BreezeBlue's Breeze TTS 2 Tops Open Weights Voice AI With 1,215 Elo
Breeze TTS 2 tops the open weights speech leaderboard with a 90 Elo lead, combining voice design, direction, and sub 140ms streaming.
BreezeBlue's Breeze TTS 2 Clones and Designs Voices in Under 40ms
BreezeBlue open-sourced a 3B bilingual TTS model that tops the Artificial Analysis leaderboard with sub-40ms latency and natural-language voice design.
Kyutai Opens Pocket TTS Training So Anyone Can Build CPU Voice Cloning
Kyutai released the full training stack for its 100M-parameter Pocket TTS, letting anyone train a voice model from scratch for under $200.
Pika Labs' Pika Speech Undercuts ElevenLabs by 9x With Studio-Quality Audio
Pika Speech is a 3B flow-matching TTS model that generates a minute of 48 kHz audio in about a second at one cent per minute.
Artificial Analysis' Speech Arena Reveals Voice AI's Uncomfortable Split Brain Problem
Artificial Analysis launched a blind human-preference leaderboard for voice agents, and the model users like most is not the one that finishes the task.
Kizuna AI Lab's Sokuji Translates Live Calls Offline Without a GPU
Sokuji is an open-source live speech translator that runs entirely on-device with WASM and WebGPU, no API key or GPU required.
Kyutai's MuScriptor Now Turns Any Song Into Printable Sheet Music
Kyutai's open-source music transcription model can now export sheet music PDFs, editable MusicXML, and guitar tabs alongside MIDI output.
Kyutai's MuScriptor Doubles Open-Source Music Transcription Accuracy to 48.2 F1
Kyutai and Mirelo's open transcription model now exports editable sheet music and guitar tabs, on top of streaming per-instrument MIDI.
No stories match these filters.