Skip to main content

InceptionLanguage modelEnterprise access

Mercury Voice

Mercury Voice has no overall index value yet because there are too few independent benchmark results.

Popularityno data yet

n/ano search or usage data

Summary

Mercury Voice targets the time to first answer token in voice agents. In its own tests on customer-service prompts, Inception reports a median of 320 milliseconds after reasoning. Despite its name, this diffusion LLM generates text; other components handle speech recognition and audio output.

Inception offers the checkpoint through its own API for enterprise customers. It handles 128K context tokens and up to 50K output tokens.

All benchmark results

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

Show all 20 published benchmark results

Page 1 of 2

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.

average quality (Show measurement, test conditions, and source)
Source value
70.5
Metric
average quality reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
tau3 Telecom (Show measurement, test conditions, and source)
Source value
77.2
Metric
tau3 Telecom reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
tau3 Airline (Show measurement, test conditions, and source)
Source value
78
Metric
tau3 Airline reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
tau3 Retail (Show measurement, test conditions, and source)
Source value
69.3
Metric
tau3 Retail reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
IFBench (Show measurement, test conditions, and source)
Source value
67.4
Metric
IFBench reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
BFCL v4 multi-turn (Show measurement, test conditions, and source)
Source value
60.5
Metric
BFCL v4 multi-turn reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
inceptionlabs.ai
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Values read from the official image-only table. Quality composite and latency use Inception's voice-agent prompts/configuration.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source inceptionlabs.ai
Average quality (MEDIUM) (Show measurement, test conditions, and source)
Source value
69
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice
Average quality (HIGH) (Show measurement, test conditions, and source)
Source value
69.9
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice
τ³-bench Telecom (MEDIUM) (Show measurement, test conditions, and source)
Source value
74.6
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice
τ³-bench Telecom (HIGH) (Show measurement, test conditions, and source)
Source value
79.82
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice
τ³-bench Airline (MEDIUM) (Show measurement, test conditions, and source)
Source value
78
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact MEDIUM column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice
τ³-bench Airline (HIGH) (Show measurement, test conditions, and source)
Source value
76
Metric
reported chart score
Unit
No unit provided
Direction
Higher is better
Source type
vendor-reported
Evaluator
Inception Labs, Introducing Mercury Voice
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. Exact product route named in the official Inception article: Mercury Voice. The chart reports the exact HIGH column label; the source does not define that label as a reasoning-effort setting. The charts show a score without a unit. No evaluation date, immutable serving revision, task denominator, or benchmark-specific protocol is published.
Context
The published cell has no 95% confidence interval. An immutable serving or weight revision and an independent replication are not stated. The source does not define Medium/High as reasoning-effort values.
Source Inception Labs, Introducing Mercury Voice

Page 1 of 2

All specifications

Architecture

Model class
Diffusion LLM for voice agents
Source: Model class

Input and output

Context window
128K tokens according to Inception
Source: Context window
Maximum output
50K tokens according to Inception
Source: Maximum output
Output
Text, not text-to-speech audio
Source: Output

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
Inception API for enterprise customers
Source: Access
Shutdown
None announced
no source

Frequently asked questions about Mercury Voice

Can I run Mercury Voice locally?

No. Inception does not publish the weights.

Stated by Inception

Open weights
no
License
n/a
Parameters
n/a
active per token
n/a

Sources and data date

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. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not published

chart score unit

Note

The source chart labels the column Score but does not define the score scale.

Unresolved

meaning of Medium/High labels

Note

The exact chart labels are retained without assuming that they denote reasoning effort.

Not published

sample count and confidence interval

Note

No task denominator or 95% interval is published.

Additional sourceInception Mercury Voice announcement (retrieved October 3, 2026; October 4, 2026; October 17, 2026) · Inception Mercury Voice announcement · Editorial description reviewed October 4, 2026
Additional sourceInception model blog (retrieved October 3, 2026) · Inception model blog · Editorial description reviewed October 4, 2026