Audio modelActive
Universal-3.6 Pro Realtime
AssemblyAI
- Released
- September 29, 2026
- Data date
- October 3, 2026
- Model class
- Access
AssemblyAI describes Universal-3.6 Pro Realtime as a direct upgrade to Universal-3.5 Pro for voice agents and telephony. The model was trained for short utterances and difficult conditions such as loud rooms, accents, and phone lines. Its API automatically detects 32 languages and sends transcript text during the conversation.
AssemblyAI uses the identifier universal-3-6-pro at its existing streaming endpoint. The list price is $0.45 per hour of audio, with volume discounts.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Streaming speech recognitionSource |
| Access | AssemblyAI APISource |
| Input | Live audioSource |
| Output | TranscriptSource |
| API model ID | universal-3-6-proSource |
| Languages | 32 languages with automatic detectionSource |
| Streaming | Real-time model for AssemblyAI's existing streaming endpointSource |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
entity error rate (Show measurement, test conditions, and source)
- Source value
- 14.4
- Score
- 14.4
- Metric
- entity error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- AssemblyAI announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Same setup
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
exact transcript rate (Show measurement, test conditions, and source)
- Source value
- 87
- Score
- 87
- Metric
- score
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- AssemblyAI announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Independent evaluation. Same public run
- Context
- The source documents a separate evaluator setup; this observation is not merged with AssemblyAI's vendor benchmark.
WER (Show measurement, test conditions, and source)
- Source value
- 5.19
- Score
- 5.19
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- AssemblyAI announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. 12,460 scripted caller scenarios, real speakers, three noise environments, 12 speaker groups; competitors via public streaming APIs at defaults and same scoring
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
lowest WER (Show measurement, test conditions, and source)
- Source value
- 2.2
- Score
- 2.2
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Coval benchmark
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Independent evaluation. Continuously updated seven-day real voice-agent window
- Context
- The source documents a separate evaluator setup; this observation is not merged with AssemblyAI's vendor benchmark.
Pipecat pooled semantic WER (Show measurement, test conditions, and source)
- Source value
- 0.96
- Score
- 0.96
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- AssemblyAI announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Independent evaluation. Public code/results, same harness; rendered 2026-09-28
- Context
- The source documents a separate evaluator setup; this observation is not merged with AssemblyAI's vendor benchmark.
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
- Price
- $0.45 per hour of audio; volume discounts availableSource
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | AssemblyAI Universal-3.6 Pro Realtime (retrieved October 3, 2026; October 4, 2026) · AssemblyAI Universal-3.6 Pro Realtime · Editorial description reviewed October 3, 2026 |
| Additional source | Coval benchmark (retrieved October 4, 2026) |