New
ElevenLabs' state-of-the-art speech recognition model for batch transcription, covering 90+ languages with word-level timestamps and diarization of up to 32 speakers. Call it through the OpenAI-compatible /v1/audio/transcriptions endpoint (json, text or verbose_json); billed by audio duration. Built for transcription services, meeting notes and content analysis.
Pricing
$0.22 per hour of input audio, billed per second, rounded up to the next whole second.
Input Modalities
- Audio
- Video
Output Modalities
- Text
Providers
ElevenLabs scribe_v2
Pricing$2$0
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today
Performance for scribe_v2
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Uptime
Loading...
Latency
Loading...
Throughput
Loading...