Read a script, or a dialogue between voices

Read words aloud: one voice reading a script (text), or a dialogue — several voices, one line each, in order (lines) — as the Voice page makes them. Priced by the characters read. Voices come from GET /api/v1/voices, models and formats from GET /api/v1/models (studio "voice"). The take comes back at once: a link (good for about 7 days) and its id, which can be the voice of a talking avatar or a story.

Key needs: create · Make things and spend credits
Price it first: POST /voiceovers/quote · free
Answers: What it made, at once

Request

curl -X POST https://vessero.com/api/v1/voiceovers \
  -H "Authorization: Bearer $VESSERO_API_KEY" \
  -H "Idempotency-Key: 47f8f6f5-ea00-4fb1-925f-76aac956a0ec" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Fresh linen, made to last.",
    "voiceId": "hpp4J3VqNfWAUOO0d1Us",
    "confirmCredits": 1
  }'

Response200 OK

{
  "status": "done",
  "take": {
    "id": "b1c2d3e4-f5a6-4b7c-8d9e-0f1a2b3c4d5e",
    "url": "https://vessero.com/f/Vt7Kq2Lm9Pa4Rx1N",
    "durationSec": 2.4,
    "voiceId": "hpp4J3VqNfWAUOO0d1Us",
    "voiceName": "Bella"
  },
  "credits": 1
}

POST/voiceovers/quoteFree

The same body without confirmCredits. It answers the price and your balance, and runs nothing.

Header

Idempotency-KeystringYour id for this request: 8–64 letters, digits, - or _. A repeat within 10 minutes gets the first answer back and never runs twice. Use the same one for the quote and the run.
Preferstringwait=N (up to 60): hold the answer up to N seconds while the job is made, within 80 seconds for the whole call.

Body

textstringOne voice reading this script, e.g. "Meet the shirt that keeps you cool all summer." Up to the model’s maxCharacters (10,000 at most). Give text or lines, not both.
voiceIdstringFor text: a voice id from GET /api/v1/voices. Default: the Voice page’s own voice.
linesobject[] · up to 100
A dialogue, read as one take: up to 100 lines and 10 voices, 10,000 characters in all. Give text or lines, not both.
- voiceIdstringrequiredThe voice reading this line, from GET /api/v1/voices.
- textstringrequiredWhat it says.
modelIdstringA voice model id from GET /api/v1/models (studio "voice"). Default: the recommended one.
stabilitynumber0–1: lower is more expressive, higher more even.
similarityBoostnumber0–1: how closely it keeps to the voice.
stylenumberOne voice only, 0–1: how much of the voice’s own style is exaggerated.
useSpeakerBoostbooleanOne voice only: lift the likeness to the voice.
outputFormatstringA format id from GET /api/v1/models (studio "voice"), e.g. "mp3_44100_128".
languageCodestringThe language it is read in, e.g. "en", where the model reads it. Default: worked out from the words.
confirmCreditsintegerrequiredThe price you agree to, in credits: the credits its quote gave. It runs at that price, or at a lower one when that figure was quoted for this Idempotency-Key; above the price now, nothing runs (409 price_changed). Left out, nothing runs and the error carries the quote.
webhookUrlstring · httpsAn https address to POST the job to once it is done or has failed, signed (see Webhooks).

Answers

200madeMade: the take, its link (good for about 7 days) and its id.
400confirm_credits_requiredA run that spends needs confirmCredits: the quote is in details.
402insufficient_creditsThe account has too few credits for this.
409price_changedThe price is above the confirmCredits sent: nothing ran; the new quote is in details.
422content_refusedThe content check refused it.
429daily_cap_reachedThe key’s daily credit cap would be passed: see Retry-After.

Next in AudioPOST/voiceovers/quotePrice it: read a script, or a dialogue between voices