Skip to content
Text to speech · Overtone

Voices that feel what they say.

34 voices in 9 accents that laugh, sigh and whisper when you tag it. 48 kHz, and it starts playing while it is still being made.

34voices9accents17feelings16sounds
Voice
Feeling

Find your voice

Every voice here is the voice the API speaks with: press play to hear its sample.

34 voices

Write it the way you’d say it

Tags in square brackets set the feeling, add a sound or change the delivery, anywhere in the line.

[nervous] [clear throat] Okay, so I may have signed us up for the neighborhood talent show. [playful] As a duet. [laughing] Don't look at me like that! [surprise] Wait, you actually said yes?

Feelings

[joy][excited][playful][tender][calm][relief][surprise][shock][sad][grief][hurt][longing][nervous][fear][angry][tired][neutral]

Sounds

[laughing][giggle][chuckle][sigh][gasp][sniff][crying][sobbing][breathing][inhale][exhale][groan][yawn][cough][clear throat][scream]

Delivery

[whisper] … [/whisper][low voice] … [/low voice][shouting] … [/shouting][tearful] … [/tearful][trembling] … [/trembling]

One call to make it speak

OpenAI-compatible: the same request shape, our voices and tags.

curl https://tts-api.yoob.com/v1/audio/speech \
  -H "Authorization: Bearer $YOOB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "yoob-tts-1", "voice": "w1243",
       "input": "[joy] You made it! [laughing] I knew you would."}' \
  --output hello.mp3
Best$0.02per 1K characters. Several takes per sentence, keeps the cleanest.
Fast$0.01per 1K characters. One take, first audio sooner, for agents.

Hear your own words

A free account writes about 5,000 characters of speech a month.