CDPR Uses AI Voice Conversion for The Witcher 3 Expansion
11/14/2026 — 11/14, 16:18·1 sources (all)·1 reports (all)
Key takeaways
- CD Projekt Red confirmed that the Polish voice of Geralt in The Witcher 3's new story expansion, Songs of the Past, will use Respeecher's AI…
- he still recorded all new lines himself, and AI adjusted his voice to resemble his earlier performances.
Background & analysis
On November 14, 2026, IT之家 reported that CD Projekt Red has confirmed that the Polish-language voice of Geralt in the new story expansion Songs of the Past for The Witcher 3: Wild Hunt will be processed with Respeecher's AI voice conversion technology. Actor Jacek Rozenek has voiced Geralt in Polish since the first Witcher game launched in 2007, but after suffering a stroke in 2019, his voice became lower and rougher.
Instead of replacing the voice actor, CDPR arranged for Rozenek to continue recording all new lines himself, with AI technology then adjusting his voice to sound close to his performances in the earlier titles. According to CDPR localization producer Mikołaj Szwed, roughly a year earlier the studio invited Rozenek to a recording studio to assess the current state of his voice. With help from the voice cloning company Respeecher, Rozenek then recorded all new lines in the normal way, and Respeecher used a voice model built from his earlier Witcher 3 recordings to convert the audio so it would match the original sound as closely as possible. Respeecher synthetic voice artist Dmytro Vasylets noted that the biggest challenge of the work lies in faithfully restoring the rich emotional range of Rozenek's performance, and the conversion process is now underway as the expansion moves forward.
AI-generated from 1 reports · updated 3 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 3 days ago
Reports on this story headlines open the original
CD Projekt Red has confirmed that Geralt's Polish voice in The Witcher 3's new story expansion, Songs of the Past, will use Respeecher's AI voice conversion technology. Voice actor Jacek Rozenek, whose voice became lower and hoarser after a stroke in 2019, recorded all his new lines himself before AI adjusted the audio to approximate his earlier performances.
IT之家AI score 58
Other stories people are talking about
- Heat index 1336RisingNvidia board not discussing Jensen Huang's return, probe into his conduct advances22 sources
- Heat index 1232RisingCalifornia Sues OpenAI Over Agents Escaping Tests, Intruding into Hugging Face15 sources
- Heat index 894Alibaba releases MoE model Qwen4-Max with 1M token context for low-cost, long-running tasks17 sources
- Heat index 665US Commerce Department issues interim final rule restricting remote access to AI chips via overseas data centers10 sources
- Heat index 528Anthropic to begin trading on Nasdaq this week under ticker ANT9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

