Powder, AI-powered clipping software that takes highlights from gaming streams and turns them into short-form videos, will soon have the opportunity to detect shouting for gamers to create even higher montages. The platform can also be working on speech-to-text software so creators can get a transcript of their entire stream and seek for keywords.
Powder has developed over 40 proprietary game-specific AI models, including audio evaluation and laughter detection, in addition to standalone models for popular titles like Fortnite, Valorant, Apex Legends, Call of Duty, Rocket League, Fall Guys, Elden Ring and Amongst Us. The corporate can also be launching a model for Counter-Strike 2.
All of the models work similarly; the AI scans the stream recordings — whether from Twitch, YouTube or an MP4 file — and finds spikes in activity, including victories, assists, kills and other performance-based in-game moments. Powder takes these highlights and creates short montages for creators to upload to social media.
Image Credits: Powder
Just like its laughter recognition capability, the platform will soon launch one other AI tool that recognizes fluctuations in voice so creators can generate clips of them shouting — a typical response when playing intense ranked matches. The corporate anticipates a mid-December launch.
“From uncontrollable laughter and rage quits to even when there’s nothing obvious happening on-screen, the most effective moments when gaming is very subjective and have to be reflected with several different perspectives that reach beyond the gameplay itself,” Powder co-founder and CEO Barthélémy Kiss told TechCrunch. “This made us certain that we wanted to capture the emotion of playing games along with your community. This mix of skill-based moments and deeply emotional moments is what makes gaming content creation so unique and special.”
Also coming to the platform next month is speech-to-text technology, giving creators a transcript of a stream and enabling them to quickly search specific words and pull up the most effective highlights. Streamers may enter mood prompts. As an example, “Find me five funny clips where my fans go crazy.” The software is tailored with gamer lingo to assist make results more accurate and precise.
“Having the ability to search and contextualize clips in long videos like Twitch streams with AI is the holy grail for content creators and the teams who support them, from their video editors to their agents and managers,” Kiss said.
Image Credits: Powder
Moreover, Powder is updating its “Community Hype” feature, which can roll out next week. The AI model launched in September and detects chat spikes. The update will recommend clips where the community “goes crazy,” Kiss said.
“The discharge of the second phase of Community Hype detection is to unlock one other perspective weighing in on what makes a ‘highlight moment’ in a stream. One dimension of that is knowing what the community, who knows a streamer best, thinks. Communities have a terrific sense of what matters in a given gaming session or stream. On this latest release, when the community goes crazy and needs to recollect a moment, that’s a moment that Powder AI will recommend you retain as a clip to share,” he explained.
In line with Powder’s survey of over 3,200 streamers, creators spend a median of 53 hours a month or 630 hours a 12 months in search of highlights and editing clips. Powder claims to avoid wasting streamers upwards of around 10 hours per week or 520 hours a 12 months.
The France-based startup was founded in 2018 by Kiss, Yannis Mangematin and Christian Navelot. It has raised $22 million up to now.