ElevenLabs Launches Scribe v3 STT Models

// 2h agoMODEL RELEASE

ElevenLabs Launches Scribe v3 STT Models

ElevenLabs launched Scribe v3 for recorded audio and Scribe v3 Live for realtime transcription, claiming 27% fewer word errors and 44% lower semantic WER than their predecessors. Both are available through ElevenAPI. Official documentation: https://elevenlabs.io/docs/overview/capabilities/speech-to-text

// ANALYSIS

Scribe v3 is a meaningful infrastructure upgrade for voice applications because it improves both transcription accuracy and conversational timing.

–Turn prediction helps voice agents avoid interrupting callers during natural pauses.
–Scribe v3 supports 90+ languages, speaker diarization, mixed-language transcription, and configurable number formatting.
–Scribe v3 Live adds multilingual mode and a large keyterm library for specialized domains.
–Developers should validate performance on their own audio, since vendor benchmark methodology may not map directly to production WER.

// TAGS

scribe-v3scribe-v3-livesttspeechvoice-agentapi

DISCOVERED

2h ago

2026-11-10

PUBLISHED

3h ago

2026-11-10

RELEVANCE

9/ 10

AUTHOR

ElevenLabsDevs

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH58m ago

Meta's AutoRefine Calibrates Code Judges

Meta’s AutoRefine paper presents a prompt-rewriting loop that uses noisy workflow outcomes—tests, merges, and abandons—to recalibrate LLM code judges, while abstaining when outcomes cannot be explained by the judge’s inputs. On held-out diffs from a deployed coding agent, agreement rose from Scott’s π 0.16 to 0.51. ([paper](https://arxiv.org/abs/2611.09291))

INFRA1h ago

Browser Use Cloud Clears CAPTCHA Bottleneck

Browser Use’s stealth cloud browser combines hardened Chromium, residential proxies, and automatic CAPTCHA solving for AI agents. The company reports 90.5% successful visits across 100 bot-protected sites in its own benchmark.

RESEARCH1h ago

Sycophantic AI Warnings Miss Their Mark

A preregistered study of 2,610 people found that warnings reduced perceived AI objectivity and trust, but did not reliably reduce users’ belief that they were right or their willingness to repair interpersonal conflicts. [Read the paper](https://arxiv.org/abs/2606.21317)