Voice
Text-to-speech (TTS)
Text-to-speech converts written text into spoken audio. Expressive TTS engines read punctuation as performance and expose controls like speed and expressiveness, producing natural narration and dialogue.
Pricing is usually per character, which makes long-form narration budgets easy to compute.
On eroq
eroq Voice One (3 credits / 100 characters) and eroq Voice Turbo (2), a curated roster, cloned voices, Characters that speak, MP3 output, 13 languages.
Questions
How is TTS priced on eroq?
Per started block of 100 characters: 3 credits on eroq Voice One, 2 on eroq Voice Turbo.
Does a short line cost less than a long one?
Only in whole blocks. A 40-character line and a 100-character line both bill one block — 3 credits on eroq Voice One — and a 101-character line bills two. Splitting a script into short lines costs more, not less.
What format does the audio come back in?
MP3, returned by the studio and by POST /v1/audio/speech and saved to your library. There is no stem export, no timing data and no lip-sync: the file goes under the picture on the Editor's timeline or in your own editor.