A 2,000-word blog post read aloud: MAI-Voice vs Sume TTS cost

A 2,000-word blog post is roughly 12,000 characters, and reading it aloud costs $0.264 on MAI-Voice-2.1, $0.18 on MAI-Voice-2.1-Flash and $0.57 on Sume TTS 1.0 in a single request.

The 12,000 figure is a planning assumption of about 6 characters per English word including the space; count the real characters of your own text before you budget, because spaces and punctuation are billed.

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.

Why one request is enough

12,000 characters sits under Sume's 20,000-character request limit, so a 2,000-word post needs one TTS job and one idempotency key.

At about 15 characters per second (a planning assumption, not a Sume figure), 12,000 characters is about 800 seconds of audio, under the 1,200-second cap. At the Sume rate the cost grows by 4.75 cents for every 1,000 characters, so an edit that adds 300 words (about 1,800 characters) adds about 9 cents on a re-run.

• Microsoft states a 45-second cap per Flash call; 12,000 characters is far past that, so Flash needs chunking while Sume does not.
• Re-voicing after an edit means a new job; keep the original job id so you can compare takes.

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.