What PixVerse documents about speech

PixVerse (docs.platform.pixverse.ai) documents a lip-sync endpoint that takes either an uploaded audio file or text read by a chosen voice, a speaker list holding built-in and custom voices, and a call that turns uploaded audio into a custom voice. The pages give no number for how long the audio or the video may be and name no language. From 4 source pages, read 2026-10-25; no maker pays to be listed.

Inclusion rule. Fields are the same five for every model here; a field the vendor does not document is recorded as not documented rather than inferred from generated output. Order. Fixed field order, identical on every model page.

1Either audio or text, and never both

A lip-sync request takes its audio one of two ways: the id of an uploaded recording, or a speaker id together with the text to be read. The page says in so many words that the two modes are not mixed, so a production chooses between a performance it already holds and a voice reading a script. The first keeps whatever the recording carries; the second makes the delivery a property of the voice picked.

Either way the video is uploaded first, and the page warns that an accepted upload may still fail the operation's own processing requirements.

2Limits that exist and are not written down

The upload page names the containers it accepts and says that each downstream endpoint imposes its own duration, codec, dimension and file-size limits. The lip-sync page does not repeat them. A production therefore learns that a ceiling exists and not where it sits, which is the position of a rejected call, reached before the call is made.

It is a number to find out before a schedule leans on it. Where an entry publishes a ceiling an editor can plan the cut; here the ceiling is discovered at the first long take.

3Two kinds of voice behind one handle

The speaker list returns built-in voices and custom ones, and either becomes a speaker id on the request. A custom voice is made through a call of its own, from an uploaded audio resource. A single handle is convenient and it flattens a distinction worth keeping: a catalogue voice is repeatable by anyone, while a custom one depends on a sample somebody has to keep safe.

Each voice record also carries a languages field and an accent, though the page names no language, and nothing states how an id is held to a character over a series, so the binding is recorded as a per-call selection.

4This entry, one column at a time

Each of these stays inside a single field: what PixVerse puts there, what the wording settles, and what it leaves for a take to answer.

• Audio source — supplied, or read from text.
• Voice source — a sample, or a built-in voice.
• Per-character binding — on the request.
• Languages — a language field, no list.
• Lip-sync — named as the endpoint's purpose.

5Read against another entry

Each of these puts PixVerse beside one other entry on a column where the two land at opposite grades of answer.

• PixVerse and D-ID — on per-character binding.

6Where this model sits against the rest

Inclusion rule. Models whose vendor documents something about generated speech. A model with nothing published on the point is still listed, with the cell marked hollow. Order. Alphabetical by model name.

Inclusion rule. Models whose vendor documents something about generated speech. A model with nothing published on the point is still listed, with the cell marked hollow. Order. Alphabetical by model name.

Inclusion rule. Models whose vendor documents something about generated speech. A model with nothing published on the point is still listed, with the cell marked hollow. Order. Alphabetical by model name.

7Sources

Taken from the lip-sync reference and voice pages at docs.platform.pixverse.ai on 2026-10-25. Every entry against the same five fields sits on the speech controls page; the rule behind each field is on how read. The entries either side of this one: Runway, SceneMixer.

• Audio source
  Audio on a lip-sync request is either the id of an uploaded audio file or both text-to-speech fields, a speaker id and the text, and the two modes are not mixeda supplied recording or text read by a voicePixVerse, Lipsync reference / recorded 2026-10-25
• Voice source
  The speaker list returns the built-in voices and the account's custom voices, and can be filtered to either kindcatalogue or supplied samplePixVerse, Get TTS Speaker List reference / recorded 2026-10-25
• Voice source
  A custom voice is created from an uploaded audio resource, and the call returns a speaker id for ita supplied samplePixVerse, Create Custom Voice reference / recorded 2026-10-25
• Per-character binding
  A speaker id taken from the TTS list is passed as the lip-sync speaker id on the request, beside the text to be reada speaker id per callPixVerse, Lipsync reference / recorded 2026-10-25
• Languages
  Each voice in the speaker list carries a languages field and an accent field, and no language is named on the pagea field on each voice, no list or countPixVerse, Get TTS Speaker List reference / recorded 2026-10-25
• Containers accepted
  Uploads accept MP4, MOV or WebM video and MP3, WAV, M4A or AAC audio, and each downstream endpoint sets its own duration, codec, dimension and file-size limitslimits left to each endpointPixVerse, Upload Media reference / recorded 2026-10-25