Sentioscope

Speech and voice controls, as each vendor documents them

Which containers and file sizes are accepted

A format and a size ceiling remove a whole class of failed call. Four entries publish them: two name a container, one caps a voice sample at ten megabytes, and one allows a hundred megabytes for audio and video alike. As of 2026-09-12.

Which ceiling binds first depends on the materialA minute of speech sits well inside a hundred-megabyte limit; a minute of high-bitrate video need not. Publishing both figures means a production discovers the binding one by arithmetic instead of by rejection.A duration ceilingA size ceilingWhat it limitsHow much performance fits one callHow heavy the file may beBinds first onDialogue: light, and longPicture: short, and heavyHow you find outBy counting words beforehandBy a rejection afterwardsWho publishes bothOne entry, for one requestOne entry, for one requestThirteen entries publish neither
Fig. 1 Cutting at a line break rather than at a limit survives a later change to either figure.
Published containers and size ceilings for audio a production hands over. Recorded 2026-09-12.
ModelWhat is documentedDetail
MiniMaxWAV or MP3Fifteen seconds in total, three clips
PixVerseOne hundred megabytesAudio and video, sixty seconds each
RunwayAt most ten megabytesA sample of ten seconds to five minutes
Wan 3.0WAV or MP3, up to fifteen megabytesOne to fifteen seconds a clip

Inclusion rule. Entries whose documentation names an accepted container or a maximum file size for supplied audio. An entry accepting audio without publishing either does not earn a row. Order. Alphabetical by model name.

1The least glamorous documentation is the most immediately useful

Nobody chooses a platform for its container support, and a team that does not know it loses a morning to rejections. Publishing WAV or MP3 with a byte ceiling settles what a production has to prepare before it writes any code.

The numbers are also small enough to be reassuring. Fifteen megabytes will hold far more than fifteen seconds of speech at any sensible bitrate, so the duration is the binding constraint and the size limit is a guard rather than a design consideration.

2A size ceiling and a duration ceiling can bind in either order

Sixty seconds and a hundred megabytes are both published for one request, and which one applies depends on the material. A minute of speech sits well inside the byte limit; a minute of high-bitrate video need not.

Treating the duration as the unit of work rather than as an upper bound avoids the problem. Scenes cut at a line break instead of at a limit survive a later change to either figure.

3Thirteen entries publish neither

Most vendors here accept audio somewhere and never say in what form. A team can usually work it out from an error message, which means the cost of the omission is a day rather than a decision.

It still belongs in the record. A vendor willing to publish a container name has documented its endpoint rather than its model, and across this register that correlates with publishing everything else.

  • Voice source
    Reference audio is capped at 15 seconds in total across at most 3 clipsa hard published limitMiniMax, video generation guide / recorded 2026-09-12
  • Voice source
    Reference audio is WAV or MP3, one to fifteen seconds a clip, fifteen seconds in total and no more than 15 MBa published capAlibaba Cloud, Wan 3.0 API reference / recorded 2026-09-22
  • Voice source
    A custom voice can be built from an audio sample between 10 seconds and 5 minutes long and at most 10 MBa published sample windowRunway, custom voices reference / recorded 2026-09-22
  • Length per call
    Audio and video are each capped at sixty seconds and one hundred megabytesPixVerse, speech and lip sync guide / recorded 2026-09-22

4Sources

Every line is read from the vendor documentation linked on the speech controls page, checked 2026-09-12. What counts as documented is on how read. Nearby: What sets the length, Charging for audio, Keeping a voice.