Eleven v3
ElevenLabs Multilingual v3. Natural prosody, emotional range, 70+ languages, inline audio tags for laughter / whisper / sigh.
Text to speechElevenLabs$0.09 / 1K charstext-to-speechelevenlabsvoicemultilingual
$0.09/ 1K chars
$0.09 per 1,000 characters. $1 ≈ 11,111 characters.
Pay only for successful generations. No idle, no minimums, no per-seat.
API
Wire it up.
Endpoint
POST https://api.tryinfer.com/v1/inference/eleven-v3/text-to-speechrequest
curl https://api.tryinfer.com/v1/inference/eleven-v3/text-to-speech \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"text": "Welcome to Infer — the inference engine for multimodal AI. One API. Every modality.",
"voice_id": "<voice_id>"
}
}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| seed | integer | — | — | — |
| text | string | Yes | — | — |
| voice_id | string | Yes | — | ElevenLabs voice id (see voice library). |
| language_code | string | — | — | — |
| output_format | string | — | mp3_44100_128 | mp3_44100_128mp3_44100_64mp3_22050_32wav_44100pcm_44100opus_48000_128 |
| voice_settings | string | — | — | — |
Authenticate with a bearer token. Get an API key →