Short-reply handling
The model is designed to deliver short German replies such as “Yes,” “Okay” and “One moment” cleanly and consistently in the same voice.
Kugel 3.5
Kugel 3.5 is KugelAudio’s text-to-speech model for voice agents and phone conversations, with controls for short replies, IPA pronunciation, timed pauses and character-by-character codes. It retains Kugel 3’s documented voices, languages, dictionaries and API while charging €0.0525 per audio minute excluding VAT, billed per second.
Text-to-speech for detail-sensitive voice interactions
Kugel 3.5 is a text-to-speech model from KugelAudio built for voice agents and phone conversations. It focuses on details that affect caller interactions, including concise replies, pronunciation of names and places, pauses that give callers time to respond, and codes that must be read character by character.
The model keeps the voices, languages, dictionaries and API used by Kugel 3. The documented setup is to select Kugel 3.5 in the dashboard or set model_id to kugel-3-5 in an API request; the product page lists the exact identifier as kugel-3.5. It is priced at €0.0525 per minute of audio excluding VAT, billed per second, which is 25% below the listed Kugel 3 rate.
Core capabilities
IPA pronunciation dictionaries
Add an IPA transcription to a pronunciation dictionary so names, brands and places are spoken according to the supplied pronunciation rather than inferred from spelling.
Timed pauses
Use a break tag to request a pause before the next sentence. The product page reports that spoken pauses stay close to the requested duration.
Character-by-character code reading
Place order numbers, licence plates and booking codes inside a spell tag to have each character spoken separately and in the written order.
Kugel 3 compatibility
Kugel 3.5 retains the voices, languages, dictionaries and API associated with Kugel 3, so the documented migration path is to change the model identifier rather than redesign the integration.
Per-second billing
Audio is priced per minute and billed by the second. The listed Kugel 3.5 rate is €0.0525 per minute excluding VAT.
Practical applications
Voice-agent call turns
Generate concise confirmations, acknowledgements and turn-taking phrases for automated callers without relying on long textual context to guide pronunciation and delivery.
Names and branded terms
Use pronunciation-dictionary entries to speak customer, company, product or place names with a supplied IPA transcription instead of depending on spelling-based guesses.
Conversational pacing
Insert requested breaks before the next sentence when a caller needs time to think, answer a question or follow an instruction during a conversation.
Transactional codes
Read order numbers, booking references, licence plates and similar identifiers one character at a time using the spell tag.
Pros and Cons
Pros
- Targets practical voice-agent details such as short replies, pronunciation dictionaries, timed pauses and spelled-out codes.
- Retains Kugel 3 voices, languages, dictionaries and API, with a documented model-ID change for migration.
- Billed by the second at €0.0525 per audio minute excluding VAT, listed as 25% less than Kugel 3.
- Published benchmark results show improvements over Kugel 3 for short German replies, IPA pronunciation, pause timing and spelled-out codes.
Cons
- The available product material does not document output formats, authentication, request and response schemas, quotas or deployment procedures.
- The strongest published benchmark evidence focuses on German and English pronunciation and phone-conversation details; broader language and workflow coverage is not specified.
- Enterprise pricing and higher concurrency options are handled separately, with no limits or account-management details provided in the source.
FAQ
What is Kugel 3.5?
Kugel 3.5 is KugelAudio’s text-to-speech model for voice-agent and phone-conversation scenarios. It focuses on short replies, IPA pronunciation, timed pauses and spelled-out codes, while retaining the voices, languages, dictionaries and API used by Kugel 3.
How do I start using Kugel 3.5?
Set model_id to kugel-3.5 in an API request, or select Kugel 3.5 from the model list in the dashboard. The product page states that existing voices, languages, dictionaries, break tags and spell tags continue to work the same way.
How is Kugel 3.5 priced?
Kugel 3.5 costs €0.0525 per minute of audio excluding VAT and is billed per second. The listed price is 25% lower than Kugel 3 at €0.07 per minute excluding VAT. Consumers in other EU countries pay their local VAT rate, shown before payment.
What controls are available for pronunciation, pauses and codes?
The model supports IPA entries in a pronunciation dictionary, break tags for requested pauses and spell tags for character-by-character reading of codes. The source does not document request and response formats, output formats or deployment steps beyond selecting the model.
Is Kugel 3.5 available to every account?
KugelAudio states that Kugel 3.5 is available to every account. Enterprise plans are priced separately on the pricing page, but the available source does not specify account quotas, concurrency limits or team-management features.
Quick Facts
- Category
- Text-to-speech API
- Provider
- KugelAudio
- Primary context
- Voice agents and phone conversations
- Model identifier
- kugel-3.5
- Pricing
- €0.0525 per audio minute, excluding VAT; billed per second
- Availability
- Available to every account; enterprise plans priced separately
Альтернативы Kugel 3.5
Fylom
Fylom is an AI podcast generator that turns a topic or question into a researched narrated episode. It supports typed or spoken prompts, voice selection, and recurring show-style listening.
Gemini 3.8 Text-to-Speech
Gemini 3.8 Text-to-Speech is Google’s pair of expressive audio models for turning scripts into customizable spoken audio. Creators, developers and enterprises can design voices, direct delivery line by line, and generate dialogue for content, dubbing and voice-agent applications.
Gemini 3.1 Flash TTS
Gemini 3.1 Flash TTS is Google’s preview text-to-speech model for generating expressive AI speech with fine-grained control over style and delivery. It is available across the Gemini API, Google AI Studio, Vertex AI, and Google Vids.
蓝藻AI
蓝藻AI是一款在线AI配音与语音合成产品，可将文字转成语音，并支持自助声音克隆。页面信息显示它面向短视频、有声书等需要配音的内容场景。
Ondoku
Ondoku 是一款基于浏览器的文字转语音软件，可将文本转换为可下载的 .mp3 语音，并提供免费额度与付费方案。它支持多语言朗读、图片朗读以及按规则商用。
Typecast
Typecast is an online AI voice generator that turns text into life-like speech with emotional delivery and a selection of hyper-realistic voices. It is a browser-based tool for creating spoken audio from written content.