PatientDesk | Spero | Text to Speech.
- PatientDesk
- Text to Voice
- $0.00002 per character
PatientDesk Spero generates US English speech from text with female or male voices.
What PatientDesk | Spero | Text to Speech is good at.
Related modelView modelGemini 3.1 | Flash | Text to Speech
Run it on the same input to compare output, speed and price.
Model documentation
About this model
PatientDesk Spero generates US English speech from text with female or male voices. Create appointment messages in MP3, WAV, FLAC, Opus, or raw PCM audio.
Questions about this model
The short answers. For anything specific to your setup, talk to our team.
PatientDesk Spero Text to Speech converts US English text into audio with a choice of female or male voices. Each request accepts up to 2,000 characters. Select spero-f1 for the female voice or spero-m1 for the male voice when preparing spoken appointment messages on each::labs.
PatientDesk Spero Text to Speech turns written appointment confirmations and reminders into spoken audio. Supply the message as text, choose a voice, and select an output format for the next step in your workflow. The model accepts US English text with a limit of 2,000 characters per request.
PatientDesk Spero supports MP3, WAV, FLAC, Opus, and PCM audio output. MP3 is the default when no output format is selected. PCM output is raw 16-bit audio at 24 kHz with one channel, so choose it when the receiving workflow expects that exact audio representation.