Text to Speech

Generate speech from text.

Voice clones — your own cloned voices. Pass a voice clone ID as voiceId.

Library voices — ready-made voices from the shared library. Pass a library voice ID as referenceId.

Character limits

Free	Pro, Premium
200 characters per generation	500 characters per generation

`sonus.tts.generate({ text, voiceId | referenceId, ... })`

Generate speech from text. Returns a sound object with a direct download link.

Name	Type	Required	Description
`text`	`string`	yes	Text to convert to speech
`voiceId`	`string`	no	ID of a voice clone you own
`referenceId`	`string`	no	ID of a voice from the shared library
`name`	`string`	no	Name for the generated sound

With a voice clone

const { sound, error } = await sonus.tts.generate({
  text: 'Hello in my cloned voice!',
  voiceId: 'your_clone_id',
})

With a library voice

const { sound, error } = await sonus.tts.generate({
  text: 'Welcome to SonusLab!',
  referenceId: 'library_voice_id',
})

sound is { id, name, audioKey, audioUrl }.

Browse voices in the shared library.

Name	Type	Required	Description
`search`	`string`	no	Filter library voices by title
`language`	`string`	no	Filter by language code
`pageSize`	`number`	no	Results per page, 1–50 (default: 20)

const { voices, error } = await sonus.tts.listVoices({ search: 'narration' })

Voice is { id, name, description, previewUrl, languages, tags }.

Clips

Extract audio segments from videos and audio across 16 platforms.

Voice Cloning

Create custom voice clones from audio samples, then use them with TTS.