SSyncDev

AssemblyAI-STT-3.7-Realtime

SyncDev model directory · Profile updated Nov 18, 2026

Compare with another model

AssemblyAI-STT-3.7-Realtime streams transcripts in 32 languages for captions, notetakers and agent assist, with final speaker labels per turn at $0.30/hour.

Key specifications

Specification score
10.0
License
Proprietary

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Indicative: $0.30 per audio hour. Confirm on your AssemblyAI account.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Audio input

Produces

  • Text output

Capabilities

Audio

What is AssemblyAI-STT-3.7-Realtime?

Not every live transcript has someone waiting on a reply. Meeting notetakers, live captions, call coaching and agent-assist screens all need text quickly, but none of them must decide the instant a speaker finishes. AssemblyAI built a separate streaming model for that job and priced it below its voice-agent variant.

AssemblyAI-STT-3.7-Realtime (assemblyai-stt-3-7-realtime) launched on 17 November 2026 at $0.30 per hour.

One stream, 32 languages

It replaces both Universal-Streaming English and Universal-Streaming Multilingual. All 32 supported languages run in a single stream with automatic detection, so a deployment that used a language router in front of two separate integrations can drop the router.

Speaker labels that do not change

Set speaker_labels: true and each turn's label is final when the turn ends. There is no later revision pass. AssemblyAI tested this on five meeting and call datasets, 466 recordings and 83 hours, against Universal-3.6 Pro Realtime:

Metric STT-3.7-Realtime Universal-3.6 Pro Realtime
DER 11.67% (live) 21.17% live / 14.96% revised
cpWER 24.25% 35.31% live / 25.84% revised

Live labels from the new model beat even the older model's revised ones.

Word accuracy

Versus the same predecessor: long-form English 8.56% WER (from 9.03%), short-form English 3.22% (from 3.44%), a 30-language average of 11.72% (from 12.25%) and 7.35% across five code-switching pairs (from 7.85%). Modest gains; the diarization change is the bigger story.

Integration notes

  • Endpoint is unchanged: wss://streaming.assemblyai.com/v3/ws, same message protocol.
  • Vocabulary help via keyterms and a 400-character prompt.
  • Partials arrive about once per second.
  • Turn-detection parameters are accepted but ignored.
  • Speaker caps depend on length: unlimited up to 2 minutes, 10 up to 10 minutes, 30 beyond.

That ignored-parameter line is the important one. Turns close when enough content has arrived, not on fast end-of-turn decisions, which is why AssemblyAI says not to put this model behind a voice agent. Use the Realtime-Agent variant for that.

A two-week trial

Shadow your current captioning or notes stream with this model for a fortnight. Compare speaker-attribution errors in the summaries people actually read, plus WER on a hand-checked sample. All numbers here are vendor-reported from launch day, and prices are indicative. Batch work belongs on the pre-recorded AssemblyAI-STT-3.7 model. For other live recognisers, compare Gemini 3.5 Transcribe Live and the wider automatic speech recognition category.

How to evaluate AssemblyAI-STT-3.7-Realtime

Compare the model on the work you need to complete.

Tasks and inputs

AssemblyAI-STT-3.7-Realtime is listed for Automatic speech recognition, Speech → Text, Speaker Diarization. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.

Frequently asked questions

Live transcripts nobody needs to answer: notetakers, captions, call coaching and agent assist. It is not designed for voice-agent turn-taking.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

assemblyai

AssemblyAI-STT-3.7

AssemblyAI-STT-3.7 is AssemblyAI's November 2026 pre-recorded transcription default: 32 languages, new diarization, fewer language flips, $0.21 per hour.

— context

assemblyai

AssemblyAI-STT-3.7-Realtime-Agent

AssemblyAI-STT-3.7-Realtime-Agent is a streaming recogniser for voice agents and IVR: 32 languages, 86 ms to final transcript, 4.46% vendor WER, $0.45/hour.

— context

salesforce

SOV-Transcribe-1

SOV-Transcribe-1 is Salesforce's open-weight speech-augmented model for non-streaming transcription, with keyword biasing and style instructions; Apache-2.0.

— context

ElevenLabs

Scribe v3 Live

Scribe v3 Live is ElevenLabs' streaming transcription model with turn prediction, mid-sentence language switching and a 10,000-term keyterm library.

— context

NVIDIA

Nemotron 3.5 Transcribe 30B A4B

Nemotron 3.5 Transcribe 30B A4B is NVIDIA's open offline ASR model: 40 languages, hour-long files, word timestamps, diarisation and translation.

65.54K context

NVIDIA

Nemotron-Labs-Unified-ASR-0.6b

Nemotron-Labs-Unified-ASR-0.6b is NVIDIA's open 600M speech recognizer for 25 European languages, running offline or streaming at down to 160 ms.

— context