#for the upcoming elevenreader v3, how will tone tags be implemented

1 messages · Page 1 of 1 (latest)

green fableBOT
#
AI-generated Answer for sierraofterra

Short answer: There’s no official documentation announcing an “ElevenReader v3” or describing tone-tag support specific to ElevenReader. What is documented is tone/emotion control in the Eleven v3 (Alpha) TTS model via “Audio Tags.” (help.elevenlabs.io)

How Eleven v3 implements “tone tags” (Audio Tags), per official docs:

  • Tags are plain words in square brackets placed inline in your text; the model interprets them to control tone, emotion, delivery, pacing, accents, non‑verbal reactions, and even SFX. Examples include [sad], [whispers], [dramatic tone], [pause], [rushed], [French accent], [sighs]. (elevenlabs.io)
  • You can insert tags anywhere in the script and combine them; they act as natural direction for performance, not SSML. (elevenlabs.io)
  • To use them via API, generate with modelId "eleven_v3" on the Create/Stream Speech (and Dialogue) endpoints. (elevenlabs.io)
  • For precise pauses, the API also supports an SSML-style break tag, e.g., <break time="1.5s" /> (up to 3 seconds). (help.elevenlabs.io)

If ElevenReader later adopts v3 under the hood, these same inline Audio Tags would be the documented mechanism—but as of today, ElevenLabs has not published implementation details for “ElevenReader v3.” (help.elevenlabs.io)

Sources:
ElevenReader – ElevenLabs
ElevenLabs Audio Tags: More control over AI Voices | ElevenLabs
ElevenLabs Audio Tags: More control over AI Voices | ElevenLabs
Eleven v3 (alpha) — The most expressive Text to Speech model
Do pauses and SSML phoneme tags work with the API? – ElevenLabs
ElevenReader – ElevenLabs

lofty cedar
#

well thats not ideal answer đź’€ i was sorta hoping the elevenreader app could auto populate the epubs with tone tags as they obviously are not traditionally in writings. could use context to insert it?

would be also neat if it could identify different characters and provide either an entirely different voice or have a tone tag be consistently applied when that character is talking like for a female narrator doing a mans voice have it be like [imitating male voice]

green fableBOT
#
AI-generated Answer for sierraofterra

Short answer: there’s no official documentation that ElevenReader auto-inserts v3 Audio Tags into EPUBs or automatically detects characters and assigns different voices. Today, Audio Tags are author-supplied directives for the Eleven v3 model, and Dialogue mode requires you to specify speakers (via the website or the Text-to-Dialogue API). (help.elevenlabs.io)

What you can do now (documented):

  • Insert Audio Tags yourself to control tone, reactions, pacing, or identity shifts (e.g., [whispers], [laughs], [deep voice], [childlike tone]). (elevenlabs.io)
  • Produce audiobooks in Studio and assign different voices to sections/speakers; you can even split a single paragraph across multiple voices. (help.elevenlabs.io)
  • Generate multi‑speaker dialogue programmatically with the Text‑to‑Dialogue API and keep character/voice mappings consistent in your code or script. (help.elevenlabs.io)

Clarification: “v3” refers to the Eleven v3 Text‑to‑Speech model, not a “Reader v3” app release. Eleven v3 adds Audio Tags and Dialogue mode; ElevenReader is the reading/listening app that uses our TTS models. There’s no published feature about automatic tone‑tagging or character detection in ElevenReader. (help.elevenlabs.io)

If we add auto tone‑tagging or character‑voice detection to ElevenReader in the future, it will be announced in the product blog or help center; there’s no such announcement in the current docs. (elevenlabs.io)

Sources:
How do audio tags work with Eleven v3 (Alpha)? – ElevenLabs
ElevenLabs Audio Tags: More control over AI Voices | ElevenLabs
What is Studio? – ElevenLabs
What is Dialogue mode? – ElevenLabs
What is Eleven v3 (Alpha)? – ElevenLabs
Eleven v3: Most Expressive AI Text to Speech Model Launched | ElevenLabs

lofty cedar
#

oh woops