The most one Sume TTS request can cost: $0.95 at 20,000 characters

The most a single Sume TTS request can cost is $0.95: 20,000 characters, the request limit, at $0.0475 per 1,000. The same characters cost $0.44 on MAI-Voice-2.1 and $0.30 on MAI-Voice-2.1-Flash.

A hard per-request ceiling is useful for budget caps: you know the worst case of any one job before you submit.

The arithmetic

Rates come from Microsoft's launch page for the two MAI voices and from Sume's public TTS rate. The Sume rate is the list-price arithmetic ($0.0475 per 1,000 characters); the live figure for your workspace is in GET /v1/catalog, and a platform fee can apply on top of list arithmetic on your invoice.

Using the ceiling as a spend cap

Because the request limit is 20,000 characters, no single TTS job can exceed $0.95. A pipeline that submits 10 jobs in parallel has a worst case of $9.50.

The MCP tool also takes dry_run to preview cost and max_spend_usd to cap it, per the tts_create description.

• At about 15 characters per second (a planning assumption, not a Sume figure), 20,000 characters is about 1,333 seconds, which is past the 1,200-second audio cap, so a full-size request can fail with tts_duration_exceeded (no credit captured). In practice, plan jobs of about 17,000 characters or fewer.
• Microsoft states Flash generates up to 45 seconds of audio per call, so the same text needs many Flash calls.

What Sume does and does not offer here

Sume does not list MAI-Voice-2.1 or MAI-Voice-2.1-Flash, so the first two rows are a price reference, not something you can call through Sume. Sume TTS 1.0 is a managed voice or avatar surface at POST /v1/tts-1.0/generate, and the TTS Router lists Sonic model ids only. A request takes up to 20,000 characters; synthesized audio over 1,200 seconds fails with tts_duration_exceeded and no credit is captured. Microsoft states the Flash model generates up to 45 seconds of audio per call, which matters for long reads.

• Long scripts: split on paragraph boundaries so each request stays at or under 20,000 characters and each audio file under 1,200 seconds.
• Output defaults to mp3 at 44,100 Hz and 128 kbps; ask for wav (pcm_s16le, 44,100) when the file feeds a render or a lip-sync step.
• Speed is a multiplier from 0.6 to 1.5 and volume from 0.5 to 2.0 in generation_config; they do not change the per-character price.

Submitting it on Sume

Paid MCP tools need an idempotency_key, and a cost-only dry run is available before you spend. Use the voice or avatar you already have, set language for any non-English text, and keep one key per item so a retry never bills twice. The tool names are tts_create for synthesis and tts_source_get for the accepted-script manifest.

Treat the table as list arithmetic. Re-check the live rate in the catalog before a large batch, because Microsoft's MAI pricing is a launch announcement dated 2026-10-01 and Sume rates are read from the repository price book as of 2026-10-08.