Inworld walks through TTS-2 voice prompting and evaluation
What happened
Aleksey Tikhonov, head of research at Inworld AI, has published a post explaining voice steering in TTS-2: you can give instructions to a voice model telling it how to deliver a line. The focus of the article is how to confirm whether those instructions actually take effect. Tikhonov says that in his tests automated audio judging proved inadequate, so the team instead measured changes in the speech itself. He also says that the wording of instructions affects the result, and that the same direction applied to different voice timbres produces different results; these metrics are used to track changes between model versions and have limitations.
AI-written from the coverage · updated 2 h ago
Coverage timeline
Follow the coverage to see the story from different sides.
- Inworld AIInworld breaks down TTS-2 voice steering and how to measure it
Inworld AI Head of Research Aleksey Tikhonov explains how voice steering in TTS-2 works: using instructions to tell a speech model how to deliver a line. The post focuses on how to measure whether those instructions actually take effect — automated audio judging fell short in its tests, so the team turned to measuring changes in the speech itself. He also discusses why instruction wording matters and why the same direction produces different results across voices; these metrics are used to track changes between model versions, and they have their limits.
Heat trend for this story
Not enough continuous observations to chart a trend yet.