Last refreshed 2026-11-18. Next refresh: weekly.
Why use STT 3.7 Realtime on AssemblyAI?
AssemblyAI offers STT 3.7 Realtime with pay-as-you-go pricing at $0.30 / hour of audio. AssemblyAI's own API for its speech-to-text (Universal) and text-to-speech models.
Audio / hour
$0.30 / hour of audio
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: assemblyai-stt-3-7-realtimeModel ID
assemblyai-stt-3-7-realtimeRequest example
Curated snippets for this provider are not sourced yet. Use AssemblyAI documentation with model ID
assemblyai-stt-3-7-realtime.Gotchas
- Use provider model ID "assemblyai-stt-3-7-realtime", not the LLMReference slug "assemblyai-stt-3.7-realtime".
Pricing
| Type | Rate |
|---|---|
| Audio hour | $0.30 / hour of audio |
Capabilities
MultimodalAudio
About STT 3.7 Realtime
AssemblyAI’s STT 3.7 Realtime transcribes live meetings, calls and captions. It supports 32 languages with automatic language detection and code switching. It supplies realtime speaker labels at turn boundaries.
Model Specs
Released2026-11-18