domains / families / media / tts

tts

separate

Generate cloned narration for the content workspace. Use local IndexTTS2 with the canonical lossless Pluviobyte reference for every local video, voice audition, digital-human narration, and subtitle-ready audio render. Preserve MiniMax only for public-facing articles or tutorials that teach users to connect through the relay service; never use MiniMax for local video production.

When to use

• local video narration
• voice audition
• digital-human narration
• subtitle-ready audio render
• public-facing articles
• tutorials teaching relay service connection

When not to use

• local video production with MiniMax
• using MP3 as speaker reference
• using MP3 as source for cloning or final subtitle timing
• falling back to macOS say or browser speech
• forwarding unapproved digital-human auditions to HeyGen

Skill page

Source