Last refreshed 2026-11-18. Next refresh: weekly.
Why use STT 3.7 on AssemblyAI?
AssemblyAI offers STT 3.7 with pay-as-you-go pricing at $0.21 / hour of audio. AssemblyAI's own API for its speech-to-text (Universal) and text-to-speech models.
Audio / hour
$0.21 / 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-3-7Model ID
assemblyai-stt-3-7Request example
Curated snippets for this provider are not sourced yet. Use AssemblyAI documentation with model ID
assemblyai-stt-3-7.Gotchas
- Use provider model ID "assemblyai-stt-3-7", not the LLMReference slug "assemblyai-stt-3.7".
Pricing
| Type | Rate |
|---|---|
| Audio hour | $0.21 / hour of audio |
Capabilities
MultimodalAudio
About STT 3.7
AssemblyAI’s STT 3.7 transcribes pre-recorded audio. It supports 32 languages with automatic language detection and code switching. It includes an updated diarization model and can fall back to Universal-2 for additional languages.
Model Specs
Released2026-11-18