AssemblyAI-STT-3.7-Realtime vs AssemblyAI-STT-3.7-Realtime-Agent
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Speech recognition | Speech recognition |
| Published capabilities | Live conversations. 32 languages in one stream with automatic detection. | Voice agents. Uses 32 languages in one stream and suppresses background conversation. |
| Access | Realtime Speech-to-Text API as assemblyai-stt-3-7-realtime | Realtime Speech-to-Text API as assemblyai-stt-3-7-realtime-agent |
| Result | Streaming transcripts with speaker labels at turn boundaries | Streaming transcript tuned for agent turn-taking |
| Billing terms | $0.30 USD per hour of audio on AssemblyAI. | $0.45 USD per hour of audio on AssemblyAI. |
| Sources | Publisher documentation · Additional documentation | Publisher documentation · Additional documentation |
| Inputs | Audio | Audio |
| Weights | Weights unconfirmed | Weights unconfirmed |
| Released | Nov 18, 2026 | Nov 18, 2026 |