Text-to-speech call
tts_callCalls a number and speaks your text with a synthetic voice, showing your caller ID. COSTS MONEY: billed per minute like any call. Returns a ref for get_tts_call.
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": {
"to": "<to>",
"caller_id": "<caller_id>",
"text": "<text>"
},
"name": "tts_call"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Phone number in international format, e.g. +447700900123 | |
| plan | No | Call plan id (optional) | |
| text | Yes | What to say (up to 1000 characters) | |
| speed | No | Speaking speed | |
| voice | No | Voice id from list_tts_voices (optional; the first voice otherwise) | |
| repeat | No | How many times to say it | |
| caller_id | Yes | Number to show as the caller | |
| voicemail | No | Also leave the message on voicemail | |
| max_duration | No | Hang up this many seconds after the answer (default: as long as the message needs) | |
| ring_timeout | No | Seconds the phone may ring, counted from when it actually starts ringing (default 60). Unanswered calls cost nothing. | |
| setup_timeout | No | Seconds to wait for the network to start ringing (post-dial delay; default 45). Never rings → failed, hangup_cause no_ringing, free. |