Synthesize speech
synthesize_speechStarts a metered text-to-speech job using an opaque plan-authorized voice handle and returns a durable operation receipt.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"voiceId": "<voiceId>",
"text": "<text>",
"idempotencyKey": "<idempotencyKey>"
},
"name": "synthesize_speech"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| speed | No | ||
| style | No | ||
| voiceId | Yes | ||
| language | No | ||
| stability | No | ||
| idempotencyKey | Yes | ||
| similarityBoost | No | ||
| useSpeakerBoost | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| operationId | Yes | ||
| submittedAt | Yes | ||
| retryAfterSeconds | Yes |