Audio edition of a weekly newsletter: 52 issues, TTS year cost
A 1,500-word issue is about 9,000 characters. A year of 52 audio editions costs $10.296 on MAI-Voice-2.1 and $22.36 on Sume TTS, per-job rounding included.
A weekly 1,500-word newsletter read aloud for 52 issues is about 468,000 characters, which costs $10.296 on MAI-Voice-2.1, $7.02 on Flash and $22.36 on Sume TTS when each issue is its own job.
Planning assumption: about 6 characters per English word including the space, so a 1,500-word issue is roughly 9,000 characters. Use your real character count.
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.
| Option | Rate | Arithmetic | Cost |
|---|---|---|---|
| MAI-Voice-2.1 | $22 per 1M characters | 468,000 x $22 / 1,000,000 | $10.296 |
| MAI-Voice-2.1-Flash | $15 per 1M characters | 468,000 x $15 / 1,000,000 | $7.02 |
| Sume TTS 1.0, 52 separate jobs | $0.0475 per 1,000 characters, rounded up to the cent per job | 52 x ceil(9000 x $0.0000475 = $0.428 to the cent) = 52 x $0.43 | $22.36 |
| Sume TTS 1.0, packed into 24 jobs | same rate, at most 20,000 characters per request | 468,000 characters in 24 requests | $22.23 |
One job per issue is the right shape
Each issue is under the 20,000-character limit, so one job per issue keeps retries simple: the idempotency key can be the issue number, and a retried send never double-bills.
Packing several issues into one request would save only a few cents across the year, but it makes a corrected issue harder to re-run alone. The table shows both so you can see the difference.
- Weekly cadence means the per-job cent rounding is paid 52 times; the rounding adds at most one cent per issue.
- If you add a 20-second spoken intro, it is part of the same character count.
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.
Sources
Related posts
More in Pricing
- Which Sume submit errors cost money: 402, queue_full, 429, 503
None of them charges you. 402 fails before the reserve, queue_full releases the hold, and rate_limited and 503 mean the job was never accepted.
- An 80-cent cap per clip: longest Sume video each model and tier allows
With a hard $0.80 ceiling per clip, which Sume video models can run, and for how long? Wan 3.0 at 480p reaches 12 s; Seedance 2.5 at 1080p cannot start.
- 100-clip batch on a Pro workspace: 24 accepted jobs, 18-job waves
On Pro a workspace holds 4 processing plus 20 queued jobs, so a 100-clip batch needs waves. Wave arithmetic for 100 six-second Wan clips costing $75.00.
- 1080p per-second vs per-clip at 7, 13 and 21 seconds: who accepts each
At 1080p a 7-second clip fits five Sume models, a 13-second clip four, a 21-second clip only Wan 3.0 and Seedance 2.5. Per-second and per-clip prices for each.
Written by Sume