TTS cost by script length on Sume: 1,000 to 20,000 characters
Sume text to speech costs $0.0475 per 1,000 characters, at least $0.01 and at most $0.95 per request. A price table by script length, plus the full-video bill.
A Sume text to speech request costs $0.0475 per 1,000 characters of transcript, with a $0.01 minimum and a $0.95 maximum, because one request holds at most 20,000 characters. Spaces and punctuation count. These numbers come from the sume/tts-1.0 catalog entry; confirm them live with GET /v1/catalog before you budget.
Price by script length
Price scales with characters, not with seconds of audio or with the voice you pick, so you can cost a script before you generate it. Count characters in your editor, including spaces.
| Transcript length | Price at $0.0475 per 1,000 | Note |
|---|---|---|
| 1,000 characters | $0.0475 | The catalog's estimate unit |
| 5,000 characters | $0.2375 | Calculated from the per-1,000 rate |
| 10,000 characters | $0.475 | Calculated from the per-1,000 rate |
| 20,000 characters | $0.95 | Largest single request |
| Very short line | $0.01 | Minimum per request |
The rest of a finished video
Voice is usually the smaller line. A captioned Short adds a caption job at $0.20 for videos up to 60 seconds, a generated music bed adds $0.125 per generation, and assembling the audio and clips on Timeline 1.0 adds $0.10 per output minute rounded up, per the Sume guides for video captions, the Music Router and Timeline 1.0.
Retakes are the real variable. Split a long script into sentences and regenerate only the line you dislike instead of the whole 20,000 characters.
Sources
Related posts
More in Pricing
- Veo 3.1 Standard, Fast and Lite: cost of 30 seconds of video
Google lists Veo 3.1 at per-second rates. Multiply them out for 30 seconds of 720p video and compare with Omni Flash's roughly $0.10 per second.
- Wan 3.0 clip price table: 2 to 30 seconds on Sume
Wan 3.0 on Sume is $0.0625, $0.125 and $0.25 per second at 480p, 720p and 1080p. A 10-second clip: $0.625, $1.25 or $2.50; 30 seconds: $1.875 to $7.50.
- Wan 3.0 price per clip: 480p, 720p and 1080p for 2 to 30 seconds
Wan 3.0 lists at $0.05, $0.10 and $0.20 per second by resolution. What a 5, 10 and 30 second clip is at list and with Sume's 1.25 multiplier.
- Which Sume API calls are free: balance, usage, catalog, filter check
Balance, usage and catalog reads cost nothing on Sume, and neither does the video-filter check. What is billed, what is refunded, and what a 402 means.
Written by Sume