Phonosphere Studio
A studio for directing synthetic speech: shape a voice's style, emotion and timing, or voice a whole two-person script in one pass.
NextAdd automated tests and documentation, then a first release.
Phonosphere Studio treats speech synthesis as a performance to direct, not a text box to fill. In the solo studio you choose a voice archetype, set its style and emotional intensity, tune pitch and speed, and mark breaths, laughs and pauses where they belong. In the screenplay studio you paste a full two-person script; each line is attributed to its speaker and the whole conversation is voiced under one style direction. When the daily quota runs out, a browser-voice fallback keeps you working.
Solo persona studio
Six voice archetypes, style and emotion intensity, pitch and speed, and prosody tags for breaths, laughs, gasps and pauses.
Dual screenplay
Paste a whole script in one block. Speakers are detected line by line and voiced as one natural conversation.
Script and voice design
An assistant tightens a rough script into a performable one, and a voice designer drafts a persona to match.
Takes you can keep
Streaming playback, a waveform player with WAV export, a live spectrum view and a history of every take.