Telexed

AI news through a solo-operator lens — only what changes your day8 of 412

FILTER[All][Agents & tools][Models & API][Generative media][Infra & SaaS][ASO & growth][Indie business][Idea signals][Other][★6+ high-signal]

clear filters

Mon, May 181 dispatches

#0412
#0412Generative media yozm_ityesterday
`Luma AI` as a Creative Agent From Planning to Execution
50radar
Luma AIAI creative agent — workflow built on in-house generation models
Creative tools usually stop at asset generation. This adds planning and coordination around Luma AI's own models, making it worth testing for repeatable content workflows.
- Luma AI is positioned as an AI creative agent platform, not just a prompt-to-asset generator.
- Its own generation models are used inside the agent flow, reducing handoff friction between ideation, production, and iteration.
- Best fit is marketing images or short-form creative pipelines where planning, variation, and coordination matter more than one-off outputs.
Source: yozm.wishket.com/magazine/detail/3740Read original →
FIG-4121:1
50radar
FIG-4121:1

Sun, May 171 dispatches

#0411
#0411Generative media GeekNews3 days ago
`SANA-WM`, a 2.6B open-source world model for 1-minute 720p video
50radar
SANA-WMOpen-source world model — generates long video from image and camera path
A single image plus a 6-DoF camera path can produce controlled long video on one GPU. Useful signal for product mockups and scene previews, but still closer to R&D than a plug-and-play SaaS feature.
- Input is one image + 6-DoF camera trajectory, so the value is controlled scene movement rather than text-to-video prompting.
- Hybrid Linear Diffusion Transformer mixes frame-level Gated DeltaNet with periodic softmax to keep long rollouts coherent.
- Single-GPU 720p 1-minute generation lowers experiment cost, but integration still depends on weights, license, and inference setup.
Source: news.hada.io/topic?id=29572Read original →
FIG-4111:1
50radar
FIG-4111:1

Fri, May 151 dispatches

#0410
#0410Generative media GeekNews5 days ago
`Supertonic 3` launches ultra-light on-device TTS with 31 languages and emotion tags
60radar
Supertonic 3On-device TTS engine — multilingual with emotion tags
A small-footprint TTS now handles expressive cues like laugh and scream, while improving pronunciation and voice cloning. Strong fit for offline narration, in-app voice UX, and cost-sensitive shipping.
- Supports 31 languages including Korean, which lowers the friction for multilingual voice features without a cloud dependency.
- Adds 10 emotion tags such as laugh, breath, and scream, so scripted dialogue can sound less flat with simple text markup.
- Pronunciation accuracy improved, and repetition or omission failures were reduced; this matters more than flashy demos in production TTS.
- Voice cloning quality also improved, making it more usable for character voices, guided audio, or branded app narration on-device.
Source: news.hada.io/topic?id=29522Read original →
FIG-4101:1
60radar
FIG-4101:1

Thu, May 141 dispatches

#0409
#0409Generative media together_ai6 days ago
`Violin`: open-source AI video translation stack
50radar
ViolinOpen-source video translation tool — unifies `ASR`, translation, and `TTS`
An end-to-end stack for multilingual video localization, not just a demo. Useful when you need ASR + translation + TTS without stitching vendors together.
- Combines speech recognition, LLM translation, and text-to-speech in one flow, reducing glue code for video localization.
- Being open-source matters more than model novelty here: you can inspect, swap, and self-host parts of the pipeline.
- Best fit is repurposing existing video assets across languages; less compelling if you only need subtitles or basic dubbing.
Source: www.together.ai/blog/violin-open-source-translation-skilRead original →
FIG-4091:1
50radar
FIG-4091:1

Wed, May 131 dispatches

#0408
#0408Generative media GitHub Trending Weekly7 days ago
`SuperSplat`: browser-based editor for 3D Gaussian Splats
50radar
SuperSplat3D Gaussian Splat editor — browser-based edit, optimize, publish
A free open-source 3D Gaussian Splat editor runs fully in the browser, covering inspection, editing, optimization, and publishing. No install lowers the barrier fast, but it matters mainly if 3D capture or spatial media is already in your stack.
- Covers the full loop: inspect, edit, optimize, and publish 3D Gaussian Splats in one web app, which cuts tool switching.
- Runs in the browser with no install, so testing workflows or client-side demos is much lighter than desktop-only tools.
- Local dev is simple: Node.js 18+, npm install, then npm run develop and open localhost:3000. Easy to fork and customize.
- Localization is already structured with static/locales plus src/ui/localization.ts, useful if you want a white-label or multilingual tool.
Source: github.com/playcanvas/supersplatRead original →
FIG-4081:1
50radar
FIG-4081:1

Tue, May 121 dispatches

#0407
#0407Generative media together_ailast week
`Voice Finder`: search and audition **600+** TTS voices faster
50radar
Voice FinderTTS voice search tool — matches by prompt or audio
Voice selection moves from manual browsing to prompt or reference-audio search. Useful if your app ships spoken UX, though it matters more for workflow speed than model quality.
- Search spans 600+ voices across Together AI TTS models, cutting the time spent comparing presets by hand.
- Natural-language prompts let you filter by tone or style, which fits rapid prototyping before wiring custom voice settings.
- Audio-sample matching is the more practical hook: upload a reference clip and shortlist similar voices faster.
- This is a discovery layer, not a new speech model. Shipping impact depends on whether voice choice is your current bottleneck.
Source: www.together.ai/blog/introducing-voice-finder-a-new-toolRead original →
FIG-4071:1
50radar
FIG-4071:1

Fri, May 81 dispatches

#0406
#0406Generative media GitHub Trending Weekly2 weeks ago
`ACE-Step UI`: polished local frontend for `ACE-Step 1.5` music generation
50radar
ACE-Step UIMusic UI — streamlines local ACE-Step generation
A Spotify-like frontend makes local AI music generation far more usable than raw model tooling. If you already have GPU headroom, free and unlimited beats paying monthly for lightweight song prototyping.
- Pairs a polished UI with ACE-Step 1.5, covering full songs, instrumentals, lyrics, batch runs, and prompt reuse in one flow.
- Pushes the strongest local pitch: no subscription, no queue limits, 100% local, which matters when iterating on many variants.
- Advanced controls go beyond consumer music apps: reference audio, cover transforms, repainting, seeds, and inference-step tuning.
- The catch is hardware and setup friction. Value is highest for creators already comfortable running GPU-heavy tools locally.
Source: github.com/fspecii/ace-step-uiRead original →
FIG-4061:1
50radar
FIG-4061:1

Thu, May 71 dispatches

#0405
#0405Generative media GitHub Trending Weekly2 weeks ago
`Pixelle-Video`: open-source pipeline for one-prompt short video production
60radar
Pixelle-VideoOpen-source video engine — one-line short-form creation
Type one topic and it writes the script, generates visuals, adds TTS, BGM, and renders the final cut. The interesting part is the modular ComfyUI pipeline, so it can become a reusable content factory, not just a demo app.
- A single prompt covers script writing, image/video generation, voiceover, background music, and final composition; it compresses the usual short-form workflow into one pass.
- Built around ComfyUI, it supports swapping pieces like FLUX, ChatTTS, GPT, Qwen, DeepSeek, and Ollama; the lock-in is lower than most hosted tools.
- Recent additions include digital avatar talking-heads, image-to-video, motion transfer, multilingual TTS voices, batch task creation, and history pages; it is moving toward an ops-ready pipeline.
- Windows gets a bundled package with no manual Python or ffmpeg setup, while macOS/Linux can install from source; that lowers trial friction for fast content experiments.
Source: github.com/AIDC-AI/Pixelle-VideoRead original →
FIG-4051:1
60radar
FIG-4051:1

`Luma AI` as a Creative Agent From Planning to Execution

`SANA-WM`, a 2.6B open-source world model for 1-minute 720p video

`Supertonic 3` launches ultra-light on-device TTS with 31 languages and emotion tags

`Violin`: open-source AI video translation stack

`SuperSplat`: browser-based editor for 3D Gaussian Splats

`Voice Finder`: search and audition **600+** TTS voices faster

`ACE-Step UI`: polished local frontend for `ACE-Step 1.5` music generation

`Pixelle-Video`: open-source pipeline for one-prompt short video production

`Voice Finder`: search and audition 600+ TTS voices faster