AI News/Wire summary
ElevenLabs explains which SSML tags its models support and what replaces the rest
Key points
- The break tag works on all ElevenLabs models except Eleven v3 and v4, with pauses up to three seconds.
- Phoneme tags for custom English pronunciation work only on Flash v2 and Turbo v2.
- Eleven v3 and v4 drop SSML entirely in favor of bracketed Audio Tags such as [whispering] and [sighs].
- WebSocket streams need enable_ssml_parsing turned on, and tags should be sent whole to avoid added latency.
Why it matters for marketers: Content teams producing voice scripts must check the model first, since break and phoneme support differs and v3 and v4 need Audio Tags instead.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
ElevenLabs: SSML tags explained: How to control pauses, pronunciation, and pacing in text to speech
Related on Z Media
- Google ships Gemini 4 Argon with tiered access and a price that doubles in NovemberOur brief, via Google DeepMind, 2 days ago
- Meta releases Muse Spark Open, runnable on two Apple Mac Studiosvia The Verge, 6 hr ago
- Google rolls out Universal Cart for US shoppers in Gemini and Searchvia The Verge, 12 hr ago
- Google Play opens to private vibe-coded apps built in AI StudioOur brief, via TechCrunch, 2 days ago
- Bluesky extends its Attie app to let anyone build websites and gamesvia TechCrunch, 6 hr ago
- Amazon launches Bee Frontier and previews Bee Eclipse with shopping tiesvia The Verge, 13 hr ago