Models/ElevenLabs/ElevenLabs V3
ElevenLabsaudio2 routes

ElevenLabs V3

ElevenLabs' most expressive voice model: lifelike narration with emotion and audio tags such as [whispers] or [laughs], and dialogue, several voices in one take. Priced by the characters read.

elevenlabs-v3Connect to ClaudeGet API key

Pricing per 1,000 characters

VariantPer 1,000 characters
All settings$0.1212 credits

Billed in credits per 1,000 characters (100 credits = $1, rounded up to a whole credit). Charged once, only for the route that succeeds. Failed attempts cost $0.00.

Request

# One Idempotency-Key per request, made once and sent again with every resend of it
KEY=$(uuidgen)

# 1. Submit. max_cost_usd is your cap: the most this may cost (it lists at $0.01).
#    No id after a timeout, a 429 or a 5xx? Run step 1 again: the same $KEY never makes a second one.
RESP=$(curl -s https://api.revana.si/v1/generations \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $KEY" \
  -d '{
    "model": "elevenlabs-v3",
    "input": {
      "text": "Nobody tells you this, but the hardest part of starting is the first five minutes.",
      "voice": "EkK5I93UQWFDigLMpZcX"
    },
    "max_cost_usd": 0.02
  }')
ID=$(echo "$RESP" | jq -r '.id // empty')
echo "${ID:-no id: ${RESP:-no answer}}"

# 2. Poll it until status is "succeeded" or "failed". A failed one is free; to try it again,
#    make a new key first (KEY=$(uuidgen)): the old one answers with the failure.
curl -s https://api.revana.si/v1/generations/${ID:?no id from step 1} \
  -H "Authorization: Bearer $REVANA_API_KEY"

# 3. Download the file once it has succeeded
curl -L https://api.revana.si/v1/generations/${ID:?no id from step 1}/content \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -o out.mp3

Set REVANA_API_KEY to your key. Full reference in the quickstart.

Options

Tasks
Text to speech
Billing unit
per 1,000 characters
Model id
elevenlabs-v3

2 routes

Every request starts on the cheapest route. If it fails, the job moves to the next one automatically.

About the ElevenLabs V3 API

How much does the ElevenLabs V3 API cost?

ElevenLabs V3 costs $0.12 per 1,000 characters on Revana. You pay in prepaid credits, 100 credits to the dollar, with no subscription or monthly minimum. A generation that fails costs nothing.

How do I call ElevenLabs V3 from code?

Send POST https://api.revana.si/v1/generations with {"model": "elevenlabs-v3", "input": {...}} and your Revana API key as a Bearer token, poll GET /v1/generations/{id} until it succeeds, then download GET /v1/generations/{id}/content. Every model on Revana takes the same request shape.

What happens if a ElevenLabs V3 generation fails?

Revana has 2 routes for ElevenLabs V3. A job starts on the cheapest and moves to the next automatically if one fails. You are charged once, only for the route that delivers. A failed generation costs $0.00.

What can ElevenLabs V3 do on Revana?

ElevenLabs V3 supports text to speech. A value it does not offer is refused with 422 before anything is charged.

Can my AI agent use ElevenLabs V3?

Yes. Connect the Revana MCP server (https://revana.si/api/mcp) to Claude, ChatGPT, Cursor or Codex, or have the agent call the REST API. The agent can list models, get a free quote and generate on your credits.

Compare with similar models

Also as markdown for agents. Every model and price: models.json.