theserverless.dev InferenceList

Models / Microsoft

Microsoft AI: MAI-Voice-2-Flash

microsoft/mai-voice-2-flash

text audioContext —

MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...

Price

No published list price.

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
Azure azure — $15/1M $0/1M — — Live openrouter-endpoints

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

No published price at list price for this workload

Every rate
UnitInputOutputFlatConfidence
token Not published— Not published— Not published— official

Price history

Microsoft AI: MAI-Voice-2-Flash
20 0 2026-09-15: $152026-09-16: $152026-09-17: $152026-09-18: $152026-09-19: $152026-09-20: $152026-09-21: $152026-09-22: $152026-09-23: $152026-09-24: $152026-09-25: $152026-09-26: $152026-09-27: $152026-09-28: $152026-09-29: $152026-09-30: $152026-10-01: $152026-10-02: $152026-10-03: $152026-10-04: $152026-10-05: $152026-10-06: $152026-10-07: $15 2026-09-15 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-09-15 token $15 $0 Not published—
2026-09-16 token $15 $0 Not published—
2026-09-17 token $15 $0 Not published—
2026-09-18 token $15 $0 Not published—
2026-09-19 token $15 $0 Not published—
2026-09-20 token $15 $0 Not published—
2026-09-21 token $15 $0 Not published—
2026-09-22 token $15 $0 Not published—
2026-09-23 token $15 $0 Not published—
2026-09-24 token $15 $0 Not published—
2026-09-25 token $15 $0 Not published—
2026-09-26 token $15 $0 Not published—
2026-09-27 token $15 $0 Not published—
2026-09-28 token $15 $0 Not published—
2026-09-29 token $15 $0 Not published—
2026-09-30 token $15 $0 Not published—
2026-10-01 token $15 $0 Not published—
2026-10-02 token $15 $0 Not published—
2026-10-03 token $15 $0 Not published—
2026-10-04 token $15 $0 Not published—
2026-10-05 token $15 $0 Not published—
2026-10-06 token $15 $0 Not published—
2026-10-07 token $15 $0 Not published—
2026-10-08 token Not published— Not published— Not published—
2026-10-09 token Not published— Not published— Not published—
2026-10-10 token Not published— Not published— Not published—
2026-10-11 token Not published— Not published— Not published—
2026-10-12 token Not published— Not published— Not published—
2026-10-13 token Not published— Not published— Not published—
2026-10-14 token Not published— Not published— Not published—
2026-10-15 token Not published— Not published— Not published—
2026-10-16 token Not published— Not published— Not published—
2026-10-17 token Not published— Not published— Not published—
2026-10-18 token Not published— Not published— Not published—
2026-10-19 token Not published— Not published— Not published—
2026-10-20 token Not published— Not published— Not published—
2026-10-21 token Not published— Not published— Not published—
2026-10-22 token Not published— Not published— Not published—
2026-10-23 token Not published— Not published— Not published—
2026-10-24 token Not published— Not published— Not published—
2026-10-25 token Not published— Not published— Not published—
2026-10-26 token Not published— Not published— Not published—
2026-10-27 token Not published— Not published— Not published—
2026-10-28 token Not published— Not published— Not published—
2026-10-29 token Not published— Not published— Not published—
2026-10-30 token Not published— Not published— Not published—

Alternatives

Call this model

OpenRouter id microsoft/mai-voice-2-flash. InferenceList does not send the request.

curl
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"microsoft/mai-voice-2-flash","messages":[{"role":"user","content":"Hello"}]}'

JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "microsoft/mai-voice-2-flash",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "microsoft/mai-voice-2-flash", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON