Synthesize text to speech

Convert text to speech audio. Returns WAV audio. Supports prosody planning and conversational mode for voice agents. Max text length: 5000 characters.

POST /v1/echo/tts/synthesize

Synthesize text to speech

cURL

curl --request POST \
  --url http://co-mind-platform-host/v1/echo/tts/synthesize \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "voice_id": "en",
  "speed": 1,
  "language": "en",
  "use_prosody": false,
  "conversational": false,
  "pacing": "normal"
}
'

200

"<string>"

Authorizations

Authorization · string · header · required

Bearer token authentication. Supports two token types:

• JWT Access Token — obtained via POST /v1/auth/login
• Personal Access Token (PAT) — created via POST /v1/api-tokens, format: cmnd_<tokenId>.<secret>

Body

application/json

text · string · required

Text to synthesize (max 5000 characters)

Maximum string length: 5000

voice_id · string · default: en

Voice ID from /v1/echo/tts/voices

speed · number · default: 1

Speech speed multiplier (0.5-2.0)

language · string · default: en

Language code (en, de, tr)

use_prosody · boolean · default: false

Enable prosody planning for natural pacing

conversational · boolean · default: false

Enable conversational mode with auto-detected presets

pacing · enum<string> · default: normal

Speech pacing for conversational mode

Available options: fast, normal, slow

Response

200

audio/wav

Audio file (WAV)

The response is of type file.