Sume TTS output: mp3, wav or raw, picked by the next step
Sume TTS defaults to mp3 at 44.1 kHz and 128 kbps; wav and raw cover editing and slicing. Pick the container, rate and encoding by what you do next.
Leave Sume TTS on its default mp3 (44.1 kHz, 128 kbps) when the file is a finished deliverable. Choose wav when you will edit or slice it, and raw when another program reads the samples directly. The container, sample rate and encoding are all request options in the API reference.
What you can set
These are the values the OpenAPI contract lists for TTS 1.0.
| Option | Allowed values |
|---|---|
| Container | mp3, wav, raw |
| Sample rate (Hz) | 8000, 16000, 22050, 24000, 44100, 48000 |
| mp3 bit rate | 32k, 64k, 96k, 128k, 192k |
| PCM encoding | pcm_f32le, pcm_s16le, pcm_mulaw, pcm_alaw |
| Default | mp3, 44100 Hz, 128 kbps |
Pick by the next step
Match the format to what happens to the file next.
- Published as-is, or attached to a post: mp3 at the default, or 192k if the track is the product.
- Cut into per-sentence files from one job: wav or raw. The reference says audio slices need wav or raw, and mp3 returns timings only.
- Joined with other audio or trimmed: wav. Sume's timeline audio route accepts wav or mp3 as its output format, and its parts must share one channel layout.
- Phone or IVR playback: 8000 Hz with pcm_mulaw or pcm_alaw, which are in the encoding list.
- Fed to a pipeline that wants samples: raw with pcm_s16le or pcm_f32le, at the rate that pipeline expects.
A sample-rate note for video
If the voice becomes the spine of a Timeline 1.0 render, a spine under 32 kHz is flagged audio_spine_low_fidelity in the docs. Keep voiceover at 44100 or 48000 Hz for video, and reserve 8000 and 16000 Hz for telephony.
The price does not change with the format: TTS is charged by characters. Pick the lossless wav when in doubt for an editing workflow, and convert at the end.
Join or trim after the fact
Because the join in timeline audio works on Sume-hosted files, a set of wav voiceover takes can be merged into one gapless file for $0.01 per job, with up to 20 parts per call. That keeps the lossless copy intact until the final export.
Sources
Related posts
More in Media tools
- Sume TTS word timestamps and sentence slices: the 70 ms boundary rule
Ask Sume TTS for timestamps.words and segmentation.mode sentence to get gapless sentence segments. The cut lands 70 ms after the last word unless you change it.
- Test a Kling motion control look on 10 seconds for $1.575, then run 30
On Sume a 10-second Kling 3.0 motion control test costs $1.575 and the full 30-second run $4.725. How to cut the test clip and what it can and cannot tell you.
- Threads video over 5 minutes: split an AI video with Sume video trim
Threads takes videos up to 5 minutes. How to cut a longer AI video into parts with POST /v1/video-trim, and what each cut costs on Sume.
- Three-minute Short: songs cap at 90 seconds, so plan the music bed
YouTube says most songs run up to 90 seconds in a 3-minute Short, some 60 or 30. Build the 180-second timeline with a voice spine and a looping, ducked bed.
Written by Sume