inputsarray · requiredOrdered dialogue turns; keep their combined text at or below 2,000 characters.
minItems: 1 · maxItems: 50
Loading tools…
Loading tools…
ElevenLabs
Generate multi-speaker dialogue audio from scripted text with voice and delivery controls.
Generate MP3 dialogue from ordered text-and-voice turns with Eleven v3. Keep each request at or below 2,000 total characters; split and stitch longer scripts agent-side.
Agents select this operation with tool ID elevenlabs.eleven-v3, then check its current inputs and price before a run.
inputsarray · requiredOrdered dialogue turns; keep their combined text at or below 2,000 characters.
minItems: 1 · maxItems: 50
charactersnumberReturned characters value.
content_typestringReturned content type value.
notestringReturned note value.
speakersnumberReturned speakers value.
Inspect returns this reviewed example, its estimated cost and the current input schema. Run calculates the estimate for your actual input.
{
"tool_id": "elevenlabs.eleven-v3",
"input": {
"inputs": [
{
"text": "[brightly] Welcome to the audio edition.",
"voice_id": "21m00Tcm4TlvDq8ikWAM"
},
{
"text": "[warmly] Here are the three ideas worth your time.",
"voice_id": "pNInz6obpgDQGcFmaJgB"
}
]
}
}{
"note": "dialogue returned as an artifact",
"speakers": 2,
"characters": 90,
"content_type": "audio/mpeg"
}invalid_input: total dialogue text must be at most 2,000 charactersSplit longer scripts into chunks of at most 2,000 characters and concatenate the MP3 artifacts agent-side.Use verified tools with pay-per-use pricing. Provider access is included. Tools that work in your own apps ask you to connect that account.
Connect your first agent to receive $1 trial credit.