Text to generate speech from.
Audio Speech Endpoints
API for text-to-speech generation.
Speech
POST /v1/audio/speech
Generate speech from text using a saved voice or a reference audio clip.
Playground
Test the endpoints live
API for text-to-speech generation.
Real world code examples
Speech
Generate speech from text using a saved voice or a reference audio clip.
Text to generate speech from.
The base64-encoded audio reference for zero-shot voice cloning.
Default Value: false
The preset or custom voice to use for generating the speech.
200 (application/json)
200 (text/event-stream)
Speech audio data.
Base64 encoded audio data
Test the endpoints live
curl https://api.mistral.ai/v1/audio/speech \
-X POST \
-H 'Authorization: Bearer YOUR_APIKEY_HERE' \
-H 'Content-Type: application/json' \
-d '{
"input": "ipsum eiusmod"
}'curl https://api.mistral.ai/v1/audio/speech \
-X POST \
-H 'Authorization: Bearer YOUR_APIKEY_HERE' \
-H 'Content-Type: application/json' \
-d '{
"input": "ipsum eiusmod"
}'200 (application/json)
200 (text/event-stream)
{
"audio_data": "ipsum eiusmod"
}{
"audio_data": "ipsum eiusmod"
}nullnull