Generate speech from text

POST 
/text-to-speech/speech

Converts the provided text to speech using the specified voice and returns audio data

application/json

Body

required

voice stringrequired

The voice ID in the format Provider.ModelId.VoiceId.

Examples:

• AWS.Polly.Joanna-Neural
• Azure.en-US-AvaMultilingualNeural
• ElevenLabs.eleven_multilingual_v2.Rachel
• Telnyx.KokoroTTS.af

Use the GET /text-to-speech/voices endpoint to get a complete list of available voices.

text stringrequired

The text to convert to speech

200: Audio data generated from the provided text

audio/mpeg

• Schema
• Example (from schema)

Schema

object

{}

401: Unauthorized

422: Invalid request parameters

Request samples

• cURL

---

curl -L 'https://api.telnyx.com/v2/text-to-speech/speech' \
-H 'Content-Type: application/json' \
-H 'Accept: audio/mpeg' \
-H 'Authorization: Bearer <TOKEN>' \
-d '{
  "voice": "string",
  "text": "string"
}'

Response samples

• 200

---

{}