Tag
Silencio-2 is an open-weight 18M-parameter TTS fine-tune of Kyutai's Pocket TTS that follows inline emotion and sound tags (laugh, sigh, whisper, angry, etc.) and runs ~20x realtime on CPU. The author shares training details and lessons, notably that an AST/AudioSet clip-level filter silently dropped rare sound events, so it was removed entirely.
NousResearch 推出 Hermes Desktop 的 ElevenLabs SFX 插件，支持直接生成音效、循环播放、一键生成变体及音效库管理，面向游戏开发场景。
Introduces a trick: hand the Openverse media search API to Claude so that, while editing videos, it automatically searches and downloads sound effects from over 5.2 million free audio tracks (mainly the 590,000 entries from Freesound via a source filter) — no API key required.
An Ask HN discussion exploring the gap in commercialized AI models for text + reference audio -> audio generation, noting that while image and text modalities are commoditized, controllable audio generation still lags behind.
The tweet demonstrates a tool that allows 'jev' to express emotions and communicate through beeps, with an audio clip attached.
StepAudio 3 Gen is a general-purpose audio generation model that unifies text-to-speech, voice design, sound effects, and music within a single discrete autoregressive framework using residual vector quantization tokens.
Amp Crash by Death By Audio is a tiny guitar amp that doubles as a distortion pedal, featuring a built-in microphone and effects to create unique, intense sounds through speaker-mic interaction.
A fun open-source tool that turns a Framework 12 laptop's hinge into a creaky wooden door sound, with pitch based on hinge position and volume based on speed.
Jordi Pons announces Stable Audio 3, a family of open-weight models for generating instrumental music and sound effects, supporting fast generation and editing on licensed audio.