Voices AI

Voices AI Live API

Version 1.2.0

Base URL: http://127.0.0.1:19470

Local REST API for programmatic control of the Voices AI Live voice changer.

The API runs on 127.0.0.1 and is only accessible from the local machine.
Enable it in Settings > Developer inside the desktop app.

Status

Query the current voice changer state

GET /v1/status

Get voice changer status

Returns the current state of the voice changer, including whether it is running and auto-pitch settings.

Responses

  • 200 - Current status
  • 401 - Invalid or missing API key

Events

Subscribe to realtime voice changer events

GET /v1/events

Stream realtime events

Opens a Server-Sent Events stream. The first event is always a status
snapshot. Subsequent events are sent whenever voice changer status,
selected voice, quality mode, or monitoring changes.

Event names and payloads:

- status: the current engine status; the initial snapshot also includes
selected voice, quality mode, and monitoring state
- voice: { "voiceId": "elon_musk" }
- quality: { "mode": "adaptive" }
- monitoring: { "enabled": true }

A keepalive comment is sent every 15 seconds while no events occur, and
SSE clients are instructed to reconnect after two seconds if disconnected.
Browser clients should use streaming fetch so the Bearer authorization
header can be included; native EventSource cannot set that header.

Responses

  • 200 - Realtime Server-Sent Events stream
  • 401 - Invalid or missing API key

Control

Start and stop the voice changer

POST /v1/start

Start the voice changer

Starts the voice changer using the currently configured audio devices and voice model.
If it is already running, this is a no-op that returns the current status.

Responses

  • 200 - Voice changer started successfully
  • 400 - Failed to start (e.g. no audio devices configured)
  • 401 - Invalid or missing API key

POST /v1/stop

Stop the voice changer

Stops the voice changer. If it is already stopped, returns the current status.

Responses

  • 200 - Voice changer stopped successfully
  • 400 - Failed to stop
  • 401 - Invalid or missing API key

Voice

Select a voice model

GET /v1/voices

List available voices

Returns all voices available in the voice library.

Responses

  • 200 - List of available voices
  • 401 - Invalid or missing API key

POST /v1/voice

Select a voice

Sets the active voice by its ID. Use GET /v1/voices to list available voice IDs.

If the voice model is not yet downloaded locally, it will be downloaded
automatically. This may take a few seconds on the first call for a given voice.

Request body

  • id string (required) - Voice ID from the voice library

Responses

  • 200 - Voice set successfully
  • 400 - Failed to download or apply voice model
  • 401 - Invalid or missing API key
  • 403 - Voice requires an active subscription
  • 404 - Voice ID not found in library

Quality

Select the voice quality and latency profile

PUT /v1/quality

Set voice quality mode

Sets the quality and latency profile used by the voice changer.
If the voice changer is running, its audio engine restarts briefly to
apply the new mode. If it is stopped, the mode is used on the next start.

Request body

  • mode string (required) - `adaptive` balances quality and latency automatically. `high-quality` prioritizes detail. `low-latency` prioritizes responsiveness.

Responses

  • 200 - Quality mode updated
  • 400 - Invalid mode or engine restart failed
  • 401 - Invalid or missing API key

Pitch

Deprecated pitch-shift controls retained for pre-v2 compatibility

PUT /v1/pitch

Set pitch shift

Deprecated in Voices AI Live v2 and later. Pitch is managed by the
v2 inference pipeline and this endpoint is retained only for compatibility.

Sets the pitch shift in semitones. Valid range is -24 to +24.
Positive values shift the voice higher, negative values shift it lower.
The voice changer must be running.

Request body

  • value integer (required) - Pitch shift in semitones

Responses

  • 200 - Pitch shift updated
  • 400 - Invalid request or voice changer not running
  • 401 - Invalid or missing API key

PUT /v1/pitch/auto

Toggle auto pitch shift

Deprecated in Voices AI Live v2 and later. Pitch is managed by the
v2 inference pipeline and this endpoint is retained only for compatibility.

Enables or disables automatic pitch adjustment.
When enabled, the app automatically calculates the optimal pitch shift
based on your voice and the selected voice model.

Request body

  • enabled boolean (required) - Whether to enable automatic pitch adjustment

Responses

  • 200 - Auto pitch setting updated
  • 400 - Invalid request body
  • 401 - Invalid or missing API key

Monitor

Control audio monitoring (hear yourself)

PUT /v1/monitor

Toggle audio monitoring

Enables or disables audio monitoring (hear yourself).
Uses the monitor device configured in the desktop app settings.
The voice changer must be running.

Request body

  • enabled boolean (required) - Whether to enable audio monitoring

Responses

  • 200 - Monitor setting updated
  • 400 - Invalid request, no monitor device configured, or voice changer not running
  • 401 - Invalid or missing API key