Speech to text with 27% fewer errors in 90+ languages
Scribe v3 is ElevenLabs’ most accurate speech-to-text model, for developers building on calls, meetings, interviews and media. It makes 27% fewer word errors than Scribe v2 across 90+ languages. Unlike transcription that breaks on noise, accents and crosstalk, it labels up to 32 speakers, tags laughter, music and emotion, boosts up to 1,000 of your own terms, detects 56 entity types and handles files up to 15 hours. For live use, Scribe v3 Live runs under 150ms.
Hunting Scribe v3 today, the new speech-to-text model from ElevenLabs.
A few numbers that stood out. On their benchmarks it lands at 5.5% WER vs 9.7% for GPT-Transcribe. Fieldy says user retention went up 50% after switching to Scribe. And it’s already running at Meta and Twilio.
If you’re testing it, skip the clean studio audio. Use your messiest call recording, add your product names as keyterms, and turn on diarization.
“Speech to text with 27% fewer errors in 90+ languages”
Scribe v3 by ElevenLabs launched on Product Hunt on November 11th, 2026 and earned 103 upvotes and 2 comments, placing #4 on the daily leaderboard. Scribe v3 is ElevenLabs’ most accurate speech-to-text model, for developers building on calls, meetings, interviews and media. It makes 27% fewer word errors than Scribe v2 across 90+ languages. Unlike transcription that breaks on noise, accents and crosstalk, it labels up to 32 speakers, tags laughter, music and emotion, boosts up to 1,000 of your own terms, detects 56 entity types and handles files up to 15 hours. For live use, Scribe v3 Live runs under 150ms.
On the analytics side, Scribe v3 by ElevenLabs competes within Artificial Intelligence and Audio — topics that collectively have 485.6k followers on Product Hunt. The dashboard above tracks how Scribe v3 by ElevenLabs performed against the three products that launched closest to it on the same day.
Who hunted Scribe v3 by ElevenLabs?
Scribe v3 by ElevenLabs was hunted by Kate Ramakaieva. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Reviews
Scribe v3 by ElevenLabs has received 232 reviews on Product Hunt with an average rating of 4.92/5. Read all reviews on Product Hunt.
For a complete overview of Scribe v3 by ElevenLabs including community comment highlights and product details, visit the product overview.
Kate Ramakaieva
Hunting Scribe v3 today, the new speech-to-text model from ElevenLabs.
A few numbers that stood out. On their benchmarks it lands at 5.5% WER vs 9.7% for GPT-Transcribe. Fieldy says user retention went up 50% after switching to Scribe. And it’s already running at Meta and Twilio.
If you’re testing it, skip the clean studio audio. Use your messiest call recording, add your product names as keyterms, and turn on diarization.
Works in the dashboard and via API, no sales call needed. Go test it https://elevenlabs.io/blog/scribe-v3