#Also, guys, do we know how long is a segment maximum duration? Based from the ElevenLab guide, it s
1 messages · Page 1 of 1 (latest)
Short answer: there is no published, platformâenforced âmaximum segment durationâ for Dubbing or Voiceover Studio.
Whatâs documented
- Dubbing Studio lets you split/merge clips and regenerate audio per clip, but no perâsegment time cap is specified. (elevenlabs.io)
- The Dubbing API allows you to create segments by arbitrary start_time and end_time; again, no duration limit is stated for a single segment. (elevenlabs.io)
- Global limits are on input length/size (e.g., up to 45 min in the UI; up to 2.5 h via API), not perâsegment length. (elevenlabs.io)
- Textâtoâspeech request limits are expressed as character caps per model (e.g., up to 40k characters â ~40 min for some models), which implies very long single generations are possible via API. (elevenlabs.io)
- Bestâpractice guidance suggests breaking long text into smaller chunks to maintain quality, but no exact duration is mandated. (elevenlabs.io)
About the âSegmenter: Max Segment duration ms: 20000â
- I canât find any public documentation that defines this UI field or ties it to a hard runtime limit. The only â20âsecondâ limit I can verify is the default inactivity timeout for the TTS WebSocket (unrelated to segment duration). (help.elevenlabs.io)
If you need to work with smaller chunks but keep natural continuity, consider Request Stitching to maintain prosody across multiple requests. (elevenlabs.io)
If you can share where you saw the 45â60s note, I can check whether itâs in an older/alternate guide; itâs not in the current public docs I searched. (elevenlabs.io)
Sources:
Dubbing Studio | ElevenLabs Documentation
Create segment | ElevenLabs Documentation
Dubbing | ElevenLabs Documentation
Models | ElevenLabs Documentation
Troubleshooting | ElevenLabs Documentation
How can I keep the WebSocket open? â ElevenLabs
Stitching multiple requests | ElevenLabs Documentation
Dubbing Studio | ElevenLabs Documentation
@proven vale
I canât find any official ElevenLabs documentation that defines a fixed âmaximum segment durationâ for Dubbing Studio. The public docs describe timeline clips/segments and paragraph-based editing, and they note a perâparagraph limit of 5,000 characters, but they do not specify any time cap per segment/clip. If youâre seeing âSegmenter: Max segment duration ms: 20000â in the UI, that value isnât documented publicly, so I canât verify it. For an authoritative answer, please contact Support. Sources: What is the timeline in Studio; Are there any limitations to the size of a project in Studio; Introducing Dubbing Studio; How can I contact support. (help.elevenlabs.io)
Sorry, I forgot to mention, the questions above are related to transcriptions.... and the (" Segmenter: Max Segment duration ms :20000") is the segment property.
Short answer: I canât find any official ElevenLabs documentation that sets a fixed âmaximum segment durationâ for Speech-to-Text transcripts or that explains a âSegmenter: Max Segment duration msâ field. The public docs show no hard perâsegment limit for transcription.
What is documented
- File limits for SpeechâtoâText: up to 3 GB and 10 hours per file. No perâsegment duration limit is mentioned. (elevenlabs.io)
- Internal chunking (for speed) is automatic for long files: audio over ~8 minutes is split and transcribed in parallel (up to 4 internal chunks). This is a processing optimization and not a userâvisible âsegment durationâ limit. (elevenlabs.io)
- The Transcript Editor lets you split/merge segments and adjust start/end times, but it does not state any maximum segment length. (elevenlabs.io)
- The SpeechâtoâText âCreate transcriptâ API lists all request parameters and likewise does not include any setting for max segment duration. (elevenlabs.io)
Recommendation
- Treat the âSegmenter: Max Segment duration ms: 20000â youâre seeing as an internal/editor control rather than a published limit. If you need the precise behavior of that UI field, please share a screenshot with support or open a ticket; thereâs no public doc for it today. In the meantime, you can freely split/merge segments in the Transcript Editor and export as needed. (elevenlabs.io)
Sources:
Speech to Text | ElevenLabs Documentation
Speech to Text | ElevenLabs Documentation
Transcripts (product guide) | ElevenLabs Documentation
Create transcript | ElevenLabs Documentation
Transcripts (product guide) | ElevenLabs Documentation
you can return to the channel and ask the AI đ
Hi Matthieu, oh, yes, you are right, I remember seeing the AI assistance, the one that looks like a...disk, I think.
Yesâthatâs our AI chatbot (powered by ElevenLabs Agents) in the bottom-right corner of the Help Center and docs. Click that circular widget to ask questions anytime. (help.elevenlabs.io)
Thanks ~~~