Qwen3 text-to-speech
speech-qwen3Nine natural voices in 10 languages, steerable with a plain-language style instruction (tone, pace, emotion). Up to 1,000 characters per call. Compared with other audio tools: budget, and one of the most used right now. Price: $0.028 per clip (up to 1,000 characters), charged only on success. One call = speech for up to 1,000 characters.
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": {
"text": "<text>"
},
"name": "speech-qwen3"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Up to 1,000 characters | |
| style | No | How to say it, e.g. 'warm and calm, slightly slower' | |
| voice | No | ||
| language | No |