ZMIME

AssemblyAI-STT-3.7-Realtime vs Scribe v3 Live

Compare documented capabilities and access. A dash means a comparable figure is unavailable.

Model specifications
SpecificationAssemblyAI-STT-3.7-RealtimeAssemblyAIScribe v3 LiveElevenLabs
TaskSpeech recognitionSpeech recognition
Published capabilitiesLive conversations. 32 languages in one stream with automatic detection.Transcribes live audio with partial results and turn prediction. ElevenLabs reports 43% fewer errors than Scribe v2 Realtime in its launch evaluation.
AccessRealtime Speech-to-Text API as assemblyai-stt-3-7-realtimeElevenLabs Speech to Text API
ResultStreaming transcripts with speaker labels at turn boundariesStreaming partial and committed transcripts
Billing terms$0.30 USD per hour of audio on AssemblyAI.Not published
SourcesPublisher documentation · Additional documentationPublisher documentation · Additional documentation
InputsAudioAudio
WeightsWeights unconfirmedWeights unconfirmed
ReleasedNov 18, 2026Nov 9, 2026