A focused feed of models, agents, research and open-source releases for people building with AI.
Idiap and Uniphore researchers show that squeezing prior conversational audio into a handful of latent tokens recovers most context-aware ASR gains while slashing prompt length.
A tiny 86k-parameter causal model estimates which notes are sounding within 50 ms of audio arriving, matching or beating much larger offline systems.
Ant Group's Ming-3.0-tts packs top-tier speech synthesis into just 0.5B parameters, released MIT-licensed and holding its own against 3.5B+ rivals.
HeyGen's new Turbo text-to-speech model takes the top blind-test ranking at $4 per million characters, undercutting its own predecessor by 7.5x.
A community-fine-tuned Slovak speech recognition model built on Meta's XLS-R has quietly racked up 860k downloads on Hugging Face.
Mistral's new speech stack combines state-of-the-art transcription, expressive TTS, and a LiveKit-based agent SDK with sub-second turn latency.
Gradium's Phonon family packs frontier text-to-speech into 31M-40M parameter models that run offline on phones, browsers, and even a Raspberry Pi 5.
Ant Group quietly dropped an MIT-licensed 0.5B TTS model that ties Fish Audio for #1 pronunciation accuracy and leads all open weights in voice cloning.
Sarvam is paying Indian creators to dub their videos into 10 regional languages, bundling free API credits with weekly content briefs and view-based payouts.
A new open dataset of 8,800 synthetic doctor-patient conversations with 1,329 hours of audio tests whether audio language models can summarize long clinical visits.
Fish Audio's new 35B mixture-of-experts TTS model takes bracketed stage directions, tops open-weight leaderboards, and ships free under a revenue cap.
A community-fine-tuned Turkish speech recognition model built on Meta's XLS-R backbone has quietly crossed 893K downloads on Hugging Face.
Meta's open-source audio generation library bundles MusicGen, AudioGen, EnCodec, MAGNeT, JASCO and AudioSeal into one PyTorch toolkit for text-to-music research.
Meta's open-source speech system covering 1,600+ languages, including 500 never before transcribed by AI, lands on TIME's Best Inventions list.
ElevenLabs launched a Video to Music API that scores footage and places matching sound effects on the cuts, with separable music and SFX tracks.
OpenAI's updated voice model adds new voices across six languages, more natural accents, and fewer awkward silences while searching.
vLLM-Omni now serves Fish Audio's 35B directable TTS model with 128 concurrent streams on one H200 and 255 ms median time to first audio.
Grok Voice 3.0 debuts at the top of the Speech-to-Speech Index with sub-second latency, better task completion than any rival, and no price hike.
A community GGUF port of OpenMOSS's 8B music understanding model lets a C++/GGML desktop app caption your own audio dataset locally.
Fish Audio's new 35B mixture-of-experts text-to-speech model ships open weights, with plain-language direction, mid-sentence voice shifts, and word-level audio inpainting.
Suno pushes a workflow-focused patch to its browser DAW with clip timestretching, smarter downbeat detection, shaped fade curves, and detachable plugin windows.
Sarvam's new Bulbul V4 Flash delivers sub-250ms Indian-language speech synthesis at a third less cost, with 83 voices across 11 languages.
A new open-source desktop app bundles IndexTTS, VoxCPM2, OmniVoice, and Qwen3-TTS for local voice cloning on Mac and Windows, with no cloud fees.
A 7.6M-parameter Turkish text-to-speech model runs 50x faster than real time on a laptop CPU, with the fewest character errors among 15 Turkish systems benchmarked.
No stories match these filters.
