TTS-1.5 is here: under 120ms latency, optimized stability! Learn more
curl 'https://api.inworld.ai/tts/v1/voice:preview?voice_id=Ashley&model_id=inworld-tts-1.5-max' \
--header "Authorization: Basic $INWORLD_API_KEY" \
| jq -r '.audioContent' | base64 -d > preview.mp3{
"audioContent": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAAAAAAAAAAAAAA..."
}Returns a short audio preview for an existing voice. The preview text is determined server-side and cannot be customized. This endpoint is not metered or billed, making it ideal for voice browsing and selection experiences. Audio is always returned in MP3 format.
curl 'https://api.inworld.ai/tts/v1/voice:preview?voice_id=Ashley&model_id=inworld-tts-1.5-max' \
--header "Authorization: Basic $INWORLD_API_KEY" \
| jq -r '.audioContent' | base64 -d > preview.mp3{
"audioContent": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAAAAAAAAAAAAAA..."
}Your authentication credentials. For Basic authentication, please populate Basic $INWORLD_API_KEY
The identifier of the voice to preview. Use the List Voices endpoint to discover available voice IDs.
"Ashley"
A successful response containing the voice preview audio.
The audio data bytes encoded as MP3. The preview text is determined server-side and cannot be customized.
Was this page helpful?