Command Palette

Search for a command to run...

Server Favicon

StableVoice

Pay-per-request text-to-speech on Modal. StableVoice serves the Chatterbox, F5-TTS, VoxCPM2, and Qwen3-TTS open models with bundled voices, optional custom voice references, mp3/wav output, and StableUpload storage slots.

npx agentcash try https://stablevoice.dev

DELETE

/api/jobs/:jobId

FREE
Soft-delete a finished StableVoice job
GET

/api/jobs

FREE
List StableVoice jobs for the authenticated wallet
GET

/api/jobs/:jobId

FREE
Get a StableVoice job status by ID

POST

/api/recording-tokens

$0.01
Mint a one-hour recording URL the recordee opens in a browser. They speak the optional suggestedText, we transcode their audio to MP3 and PUT it into the StableUpload slot you reserved. The slot's publicUrl is what you'll plug into /api/speech as referenceAudioUrl. Pass StableUpload uploadUrlExpiresAt as expiresAt so the recording URL never outlives the upload slot. Advanced callers may pass requestedExpiresAt only when they also reserved a matching longer StableUpload upload URL and pass its uploadUrlExpiresAt as expiresAt.

POST

/api/speech

Dynamic
Create a paid StableVoice TTS job. Reserve an output slot on stableupload.dev first, then pass that slot as output. Poll /api/jobs/{jobId} until result.outputs.audio.publicUrl is ready.

GET

/api/voice-samples

FREE
List static StableVoice MP3 previews for every bundled voice. Use this before choosing a bundled voice for /api/speech.

GET

/api/voices

FREE
SIWX StableVoice model and voice catalog. Every voice in `voiceGuide` leads with an accent/ethnicity tag (Indian, Australian, Slavic, Black, Latina, American, older country, etc.) and a one-line casting cue, so an agent can match a voice to a character's identity rather than only to a use case.

Install on Your Agent

Add StableVoice skills to any client

npx agentcash add https://stablevoice.dev
Transactions
Volume
Agents