Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
Official provider results

Realtime TTS-2 Flash launch notes

Inworld’s model documentation reports time-to-first-byte and coverage for the Flash variant of Realtime TTS-2.

Source snapshots refreshed
Five measurement lanesVOICE / S2S

Reasoning, task completion, conversation dynamics, experience, and latency stay separate.

Back to directory

Benchmark profile

Scope
Time-to-first-byte and language coverage from the official model docs
Primary metric
Latency (lower is better)
Owner
Inworld
Available evidence
Documented figures only

What it measures

Latency
How long do responses, tool calls, and full tasks take?

Available results

Time to first byte
20 ms
Documented

5x faster than Realtime TTS-2.

Languages
200+
Documented

Same coverage as Realtime TTS-2.

Price
$15 per 1M characters
On-demand plan

Growth $7; enterprise sub-$5.

Interpretation limit

Provider-documented latency; no arena or listening-test result is published for the Flash variant.