Sociaro

elevenlabs/eleven_multilingual_v2

ElevenLabs Multilingual v2 text-to-speech: lifelike speech of consistent quality, the most stable on long-form text, in 29 languages, up to 10,000 characters per request.

Slugelevenlabs/eleven_multilingual_v2
Kindaudio
Vendorelevenlabs
EndpointPOST /v1/audio/speech

Charged per job from what the generator reports it rendered — your Logs show the exact figure for each one; see balance and billing.

Calling it

curl https://api.sociaro.com/v1/audio/speech \
  -H "Authorization: Bearer $SOCIARO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "elevenlabs/eleven_multilingual_v2",
        "input": "Hello from Sociaro.",
        "voice": "alloy",
        "response_format": "mp3"
      }' \
  --output speech.mp3

Parameters

FieldTypeRequiredDefaultValuesWhat it does
inputstringyes—text, within the model's character limit (above)What to say.
voicestringyes—an ElevenLabs voice id, or alloy · amber · ash · august · blue · coral · lily · onyx · sage · verseThe OpenAI-style names are mapped to ElevenLabs voices (alloy is Rachel, ash is Domi, coral is Aria, …); any other value is passed on as a voice id.
response_formatstringnopcm (44.1 kHz)mp3 · pcm · opus, or an ElevenLabs output format such as mp3_44100_128mp3 is 44.1 kHz at 128 kbps and opus 48 kHz at 128 kbps. Send mp3 for a playable file: the default is raw PCM.
speednumberno1.0ElevenLabs' range, 0.7 – 1.2Speaking rate, passed to the voice settings.