Skip to main content

Amazon Web ServicesAudio modelActive

Amazon Nova 2 Sonic

Popularityno data yet

n/ano search or usage data

Summary

Amazon Nova 2 Sonic is Bedrock’s speech-to-speech model for bidirectional real-time conversations. It accepts audio and text and returns both. Turn taking and expressive polyglot voices belong to the conversation model, while asynchronous tools run alongside the audio exchange.

AWS cites a one-million-token context and availability in US regions and Tokyo. Audio and text tokens are billed separately at the applicable Bedrock rate. It is a hosted Bedrock service rather than a local weights checkpoint.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 71 published benchmark results

Page 1 of 6

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.

Big Bench Audio accuracy (Show measurement, test conditions, and source)
Source value
87
Metric
accuracy
Unit
%
Benchmark version
Nova 2 technical report Table 12; Big Bench Audio version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Artificial Analysis evaluation of speech-to-speech models
Context
Artificial Analysis is named in Amazon's report; this record preserves Amazon's report rather than an independently retrieved leaderboard run.
Source Amazon Nova 2 technical report
BFCL accuracy (Show measurement, test conditions, and source)
Source value
74.5
Metric
accuracy
Unit
%
Benchmark version
BFCL-v3 filtered snapshot, repository commit c67d246
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. single-turn, single-function, python-only subset; text prompts transformed with Google TTS; report explicitly cites BFCL state as of 2025-03-02
Context
The cited 2025-03-02 BFCL snapshot is a dataset state, not a Nova 2 Sonic run date.
Source Amazon Nova 2 technical report
ComplexFunction accuracy (Show measurement, test conditions, and source)
Source value
65.2
Metric
accuracy
Unit
%
Benchmark version
ComplexFunction; version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. text prompts transformed with Google TTS
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
IFBench prompt-level accuracy (Show measurement, test conditions, and source)
Source value
33.3
Metric
accuracy
Unit
%
Benchmark version
IFBench; version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. text prompts transformed with Google TTS
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
IFBench instruction-level accuracy (Show measurement, test conditions, and source)
Source value
37.5
Metric
accuracy
Unit
%
Benchmark version
IFBench; version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. text prompts transformed with Google TTS
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, American English masculine, versus GPT-Realtime (Show measurement, test conditions, and source)
Source value
53.9
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, American English masculine, versus Gemini 2.5 Flash Live (Show measurement, test conditions, and source)
Source value
60
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, Indian English masculine, versus GPT-Realtime (Show measurement, test conditions, and source)
Source value
55.5
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, Indian English masculine, versus Gemini 2.5 Flash Live (Show measurement, test conditions, and source)
Source value
64.2
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, Spanish masculine, versus GPT-Realtime (Show measurement, test conditions, and source)
Source value
68.4
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, Spanish masculine, versus Gemini 2.5 Flash Live (Show measurement, test conditions, and source)
Source value
70.3
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report
Human preference, French masculine, versus GPT-Realtime (Show measurement, test conditions, and source)
Source value
54.7
Metric
win rate
Unit
%
Benchmark version
Nova 2 technical report Table 11; preference test version not stated
Category
audio
Direction
Higher is better
Source type
vendor-reported
Evaluator
Amazon Nova 2 technical report
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. human evaluation; rows are winning rates for Nova 2 Sonic against GPT-Realtime / Gemini 2.5 Flash Live
Context
Source-specific observation; it does not establish a compatible cross-model cohort.
Source Amazon Nova 2 technical report

Page 1 of 6

All specifications

Architecture

Model class
Speech-to-speech conversation
Source: Model class

Input and output

Input
Audio and text
Source: Input
Output
Audio and text
Source: Output
Capabilities
Expressive polyglot voices, turn-taking control, and asynchronous tools
Source: Capabilities

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Amazon Bedrock API
Source: Access
Shutdown
None announced
no source

API

API model ID
amazon.nova-2-sonic
Source: API model ID

Further details

Transport
Bidirectional streaming in Amazon Bedrock
Source: Transport
Regions
US East, US West, and Tokyo
Source: Regions

Prices

Billing
Separate token rates for audio and text input and audio and text output; text rates also apply to transcription, tool calls, grounding, and history. Standard, Priority, and Flex tiers must be checked separately.Source

Sources and data date

Show all 10 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Research statusResearch date October 4, 2026. 8 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published

dai-s2s-st-model-specific-rater-count

Original wording

DAI-S2S-ST publishes 819 prompts and about 153,000 ratings across the evaluation, but not the Nova 2 Sonic count by metric. No model-specific N is assigned.

Not published

dai-s2s-st-serving-build

Original wording

The exact Bedrock model ID is documented, but no immutable backend serving revision is published.

Additional sourceAWS Amazon Nova 2 Sonic announcement (retrieved October 3, 2026) · AWS Amazon Nova 2 Sonic announcement · Editorial description reviewed October 3, 2026
Additional sourceAWS Nova pricing (retrieved October 3, 2026) · AWS Nova pricing · Editorial description reviewed October 3, 2026
Additional sourceAmazon Nova 2 technical report (retrieved October 4, 2026; October 24, 2026)
Additional sourceCekura Bench (retrieved October 17, 2026; October 18, 2026)
Additional sourceDavid AI Research DAI-S2S-ST (retrieved October 17, 2026)
Additional sourceAWS AI Service Card: Amazon Nova 2 Sonic (retrieved October 17, 2026)
Additional sourceCekura Bench turn-taking benchmark (retrieved October 18, 2026)
Additional sourceDuplexWorld (retrieved October 18, 2026)
Additional sourceAWS Machine Learning Blog, Loka customer case study (retrieved October 18, 2026)
Additional sourceModel metadata (retrieved October 17, 2026)