Clean and improve noisy recordings before they are published or reused in downstream workflows.
Build with SonicVox
Text to speech, voice cloning, dubbing and transcription — in the app or over the API. Start with a guide, or make your first API call in a couple of minutes.
Your first API call
Full API reference →Create a key in Settings → API Keys (it is shown once), then pick a voice and speak a line. Both calls below run as-is.
# 1. Find a voice
curl https://api.sonicvox.ai/api/v1/voices?page_size=1 \
-H "sv-api-key: $SONICVOX_API_KEY"
# 2. Speak a line in it
curl https://api.sonicvox.ai/api/v1/text-to-speech \
-H "sv-api-key: $SONICVOX_API_KEY" \
-H "content-type: application/json" \
-d '{"text":"Hello from SonicVox.","voice_id":"<voice_id from step 1>"}' \
--output hello.wavFeatured guides
Start here if you are new.
Launch SonicVox quickly, understand credits, and move from your first voice to your first production workflow.
Turn scripts into spoken audio with selectable voices, generation history, and reusable outputs.
Create reusable custom voices from short recordings and reuse them across the SonicVox stack.
Generate and manage custom SFX from text prompts, then reuse them in Studio or other projects.
Transcribe recordings, diarize speakers, capture subtitles, and export structured text outputs.
Assemble TTS, SFX, imported audio, and generated clips into one production workflow.
Build, deploy, and monitor voice agents, live calls, and workflow-driven conversations.
Recently updated
The latest changes to these guides.
Create reusable custom voices from short recordings and reuse them across the SonicVox stack.
Convert one voice into another style or target identity using the speech-to-speech workflow.
Get told before a workspace runs out, and configure how the workspace behaves by default.
Fetch supported web content and turn it into audio in one flow.
Turn text into audio over HTTP. Pick a voice, post your text, get a WAV back.
Browse all guides
Every guide, by area. Last updated Aug 11, 2026.