Eleven v4

For expressive ad reads, narration and character lines. Emotion tags guide the delivery of the selected voice. Sections up to 2,000 characters are recommended for manageable takes; the request limit is 10,000.

Cost

8 tokens/1,000 characters

ImageProvider: ElevenLabs

Try Eleven v4 in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Create in a project Open in playground Use through API

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation

IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","model":"elevenlabs-tts-v4","input":{"prompt":"studio portrait of a red corgi, soft light","stability":0.5,"similarity":0.75}}'

Input fields

* required

Field	Type	Default	Allowed
prompt*`prompt` Voiceover script/text to speak.	string	—	up to 10000 chars
voice*`voice` Voice id from GET /api/v1/voices.	string	—	string
stability`stability` Controls consistency of delivery.	number	0.5	from 0 · up to 1 · step 0.01
similarity`similarity` Controls how closely the output follows the selected voice.	number	0.75	from 0 · up to 1 · step 0.01

prompt*prompt

Voiceover script/text to speak.

Type: string
Default: —
Allowed: up to 10000 chars

voice*voice

Voice id from GET /api/v1/voices.

Type: string
Default: —
Allowed: string

stabilitystability

Controls consistency of delivery.

Type: number
Default: 0.5
Allowed: from 0 · up to 1 · step 0.01

similaritysimilarity

Controls how closely the output follows the selected voice.

Type: number
Default: 0.75
Allowed: from 0 · up to 1 · step 0.01

Cost

8 tokens/1,000 characters

Capabilities

Modestext_to_speech

Get API key