ElevenLabs Text-to-Speech
View schema →
elevenlabs.ttsGenerate realistic spoken audio (MP3 base64) from text using ElevenLabs.
Tool ID: deepgram.tts
Generate low-latency spoken MP3 audio from text using Deepgram Aura.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Required | Text to synthesize into speech (MP3 returned as base64) |
model | string | Required | Deepgram Aura voice model |
curl -X POST https://helve.dev/v1/tools/call \
-H "Authorization: Bearer sk_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"tool_id": "deepgram.tts",
"arguments": {
"text": "Your tool call completed successfully.",
"model": "aura-2-thalia-en"
}
}'
call_tool){
"name": "call_tool",
"arguments": {
"tool_id": "deepgram.tts",
"arguments": {
"text": "Your tool call completed successfully.",
"model": "aura-2-thalia-en"
}
}
}
elevenlabs.ttsGenerate realistic spoken audio (MP3 base64) from text using ElevenLabs.
elevenlabs.sound_effectsGenerate custom MP3 sound effects from a text prompt via ElevenLabs.