ElevenLabs Scribe v2
ElevenLabs’ second-generation speech-to-text — 90+ languages, speaker diarization and sub-200ms streaming.
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Radar-Achsen sind aus Kategorie-Scores approximiert, wo direkte Benchmark-Messungen fehlen — siehe Methodik.
Stärken & Trade-offs
Wo das Modell gewinnt
- Top-tier WER across 90+ languages
- Realtime partials fast enough for barge-in agents
- Built-in diarization — no extra pipeline
Worauf achten
- STT only — pair with an LLM and TTS for full loops
- Per-minute pricing adds up on call centers
- No on-prem option
Killer-Anwendungsfälle
Developer-Quickstart & API
ELEVENLABS_API_KEY — API-Schlüssel holencurl -X POST "https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID" \
-H "xi-api-key: $ELEVENLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text": "Welcome to the future of voice agents.", "model_id": "scribe_v2"}' \
--output speech.mp3import os, requests
resp = requests.post(
"https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID",
headers={"xi-api-key": os.environ["ELEVENLABS_API_KEY"]},
json={"text": "Welcome to the future of voice agents.", "model_id": "scribe_v2"},
)
open("speech.mp3", "wb").write(resp.content)const res = await fetch("https://api.elevenlabs.io/v1/text-to-speech/VOICE_ID", {
method: "POST",
headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY, "Content-Type": "application/json" },
body: JSON.stringify({ text: "Welcome to the future of voice agents.", model_id: "scribe_v2" }),
});
await fs.promises.writeFile("speech.mp3", Buffer.from(await res.arrayBuffer()));Text-to-speech — replace VOICE_ID with a voice from your library; returns an audio stream.
Offizielle Ressourcen & Links
Hosts & Latenz vergleichen
Durchsatz, TTFT und Cache-Preise bei Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock und Azure.
Ergebnisse nach Quelle
Kategorie-Punkte
Benchmark-Ergebnisse
Direkte Live-Duelle
Live-Spezifikationen & Architektur
- 90+ languages with automatic language ID
- Speaker diarization and word-level timestamps
- Sub-200ms partial transcripts for live agents
- Noise-robust far-field microphone handling
Geschätzte Monatsrechnung
Zitieren & Einbetten
Loading badge markdown...@misc{llmpodium2026elevenlabsscribev2,
title = {Benchmark Analysis and Intelligence Evaluation of ElevenLabs Scribe v2},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/elevenlabs-scribe-v2}
}Score-Badge einbetten
Fügen Sie Ihrem GitHub- oder Hugging-Face-README ein Live-Podium-Score-Badge hinzu — es verlinkt auf das Live-Ranking.
Loading badge snippet...Loading badge snippet...Mehr von ElevenLabs
Alternative Modelle
Nächste Alternativen zu ElevenLabs Scribe v2 basierend auf Leistung, Preis und Benchmarks.