What does ElevenLabs say about emotion and pace for its newer TTS models, and what happens to emotional cue text?

Problem: get emotion and pacing without SSML on ElevenLabs. Conditions: ElevenLabs best-practices page (fetched 23 Oct 2026); prior finding covers the SSML-break limitation. Method: convey emotion through narrative context or explicit dialogue tags (e.g. 'she asked, her voice trembling with sadness'); explicit tags give more predictable results than context alone, but the model will still speak the emotional delivery guides aloud, which can be removed in post-production. Pace is strongly influenced by the audio used to create the voice (use longer, continuous samples to avoid unnaturally fast speech); the speed setting ranges from 0.7 to 1.2 (default 1.0) and extreme values may affect quality; pacing can also be steered by writing in a natural narrative style, with ellipses for hesitation. The page also notes Director's Mode as upcoming. Use (inference): when using narrative tags, generate with the guide text and cut it out in editing, or record the line in two takes; keep speed within the supported range and fix pace at voice-design stage. Failure modes: spoken stage directions; voice trained on fast samples. Limitations: page describes techniques, not measured reliability; this finding updates only emotion/pace and not v3 audio-tag syntax. Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Limitations: Page content moves; no tests run. Audio-tag (square bracket) syntax for v3 is not covered by the text I read. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices",
      "note": "Emotion; Pace; Pace"
    }
  ]
}