Changelog
KugelAudio changelog: new text-to-speech models, API features, SDK releases and integrations, newest first, each entry linking to the page that documents it.
What you can do with KugelAudio that you could not do before, newest first. Each entry links to the page that documents it.
2026-10-21
- Integrations
- SDKs
2026-10-13
- Models
- Voices
Kugel 3.5 is the default model
kugel-3.5is the default text-to-speech model when a request sends nomodel_id. Sendkugel-3to stay on the previous model. See Models.- Creating a voice clone or adding reference audio to one now needs the
speaker's consent: the required
speaker_consentfield in the API and SDKs, or a checkbox in the dashboard. See Speaker consent.
2026-10-09
- API
- Integrations
Projects over the API and the MCP server
- Platforms that serve several end customers can create one project per customer and issue and revoke its API keys over the API. See Projects.
- Connect Claude, Cursor and other MCP clients to your KugelAudio account. See MCP server.
2026-10-06
- API
- Account
API key permissions
- Limit each API key to the resources it needs. See Key permissions.
2026-10-04
- Dashboard
Error alert emails
- Turn on Error alerts for a project to get an email when its text-to-speech requests fail. See Get an email when requests fail.
2026-10-01
- Account
Email when credits run out
- Organization owners and admins get one email when the organization's credits run out. See Errors.
2026-09-30
- Speech enhancement
Clarity leaves preview
- Speech enhancement with
clarity-1is no longer a preview. - One WebSocket connection can carry several audios, one after another. See Several audios on one connection.
2026-09-29
- Speech enhancement
- SDKs
- Integrations
Speech enhancement with Clarity 1
clarity-1removes background noise from speech, or keeps one speaker's voice and removes every other voice and sound, for recordings and for live audio. See Speech enhancement.- Every organization starts with a free month of Clarity, then switches to paid. See Free month and paid plan.
- Python SDK 2.2.0 and JavaScript SDK 1.2.0 add speech enhancement. See the SDK reference.
- The LiveKit and Pipecat integrations can remove background noise from incoming audio before your agent hears it.
2026-09-24
- Account
Two-factor authentication and passkeys
- Protect your account with an authenticator app or a passkey, sign in with a passkey, and let your organization require two-factor authentication. See Account security.
2026-09-23
- SDKs
- API
- Voices
Python SDK 2.1.0, JavaScript SDK 1.1.0, Java SDK 3.1.0
GET /v1/voicestakes alanguagefilter:dereturns every German voice,de-ATonly Austrian German. See Voices.- The SDKs send
project_id, so a project's pronunciation dictionaries apply to SDK requests, including the Python LiveKit and Pipecat plugins. See Dictionaries. - The SDKs report their own failures to KugelAudio, and you can turn this off. See SDK diagnostics.
- The Python SDK requires Python 3.10 or newer.
2026-09-15
- Dashboard
Request logs in the dashboard
- The Logs page of each project lists its text-to-speech requests with their status, error code, cost and a trace ID to quote to support. See Find a request in your logs.
2026-09-14
- Integrations
2026-08-21
- Integrations
Cognigy Voice Gateway
- Use KugelAudio voices in Cognigy flows through Voice Gateway, with voice style and text normalization settings. See Cognigy.
2026-08-17
- SDKs
Detect the watermark offline
- The Python SDK's
watermarkextra checks a WAV file for the KugelAudio watermark without a network call. See Detecting the watermark.
2026-08-10
- Integrations
- SDKs
Speed in the LiveKit plugins
- The LiveKit plugins take a
speedoption (Python SDK 1.9.0, JavaScript SDK 0.10.0). See LiveKit.
2026-07-30
- Speech markup
Spelled codes are grouped
- Codes with digits inside
<spell>tags are read in groups of four characters with a short pause between groups, the way a person reads a code aloud. See Spell.
2026-07-26
- API
AI-generated audio marking
- All cloud text-to-speech audio carries an in-band watermark and a disclosure header that mark it as AI-generated. See AI-generated audio marking.
2026-07-21
- SDKs
Python SDK 1.7.0
- Change
cfg_scale,speedortemperaturebetween turns of a Python streaming session withupdate_settings(). See Streaming.
2026-07-08
- Integrations
- SDKs
LiveKit for TypeScript, JavaScript SDK 0.9.0, Java SDK 2.4.0
2026-06-11
- Speech markup
Per-span speed
- Speed up or slow down part of a text with
<prosody rate>. See Per-span speed.
2026-06-10
- API
- SDKs
Dictionaries per request, end-of-audio frame
- Choose which pronunciation dictionaries a request uses. See Choose dictionaries per request.
- Streaming sessions send a final frame after the last audio of a turn, so you know the turn's audio is complete (Python SDK 1.6.0, JavaScript SDK 0.8.0). See Turn lifecycle.
2026-06-08
- API
- SDKs
Telephony formats and per-session usage
- Request G.711 ยต-law or A-law audio at 8 kHz for phone calls with
output_format. See Audio formats. - WebSocket sessions report their audio time and cost when they close, so you can bill your own customers per conversation. See Per-session usage.