Upload the recordings
Add one or more files in any of the nine supported formats.
ACTIVE · VERIFIED AGAINST THE PRODUCT
Speech to Text
Transcribe audio with ElevenLabs Scribe v2 and export readable text, SRT subtitles or structured timing data.
Verified operating specifications
Real inputs, limits and controls
- Upload limit
- 200 MB per audio file
- Formats
- AAC, AIFF, OGG, MP3, Opus, WAV, WebM, FLAC and M4A
- Outputs
- SRT segments plus JSON segment and word timing
- Detection
- Optional audio-event tagging; multi-file batch and ZIP download
Core capabilities
What this tool does
Scribe v2
SRT export
Structured timing data
Audio upload
Connected services
Related voice sources, services or models
ElevenLabsConnected serviceProduct workflow
From input to finished output in three steps
Choose transcription detail
Enable audio-event tags when non-speech sounds matter.
Export timed text
Download SRT or structured JSON individually or as a batch ZIP.
Use cases
Good fits
- Subtitle creation
- Podcast transcripts
- Interview analysis
- Word-level timing data
Developer API
Integrate this workflow
Generation tasks are asynchronous: receive a task_id, then poll or use a webhook.
POST/v1/task/speech-to-textProduct-verified information
This page only describes capabilities visible in the current application with a corresponding processing path at the latest verification.