Frequently asked questions
Who runs EchoQuest?
EchoQuest is an independent storefront for the same text-to-speech API, operated as a standalone entity. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our focus is providing a reliable API endpoint for freelance game developers without corporate overhead or external branding constraints.
Are the voices licensed?
Yes. Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures legal clarity for your game audio assets while maintaining high-quality synthetic speech generation suitable for NPC dialogue and environmental narration.
Do you use my data for training?
No. Input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We prioritize your data privacy, ensuring your unique NPC lines remain exclusive to your project without being reused for model improvement.
How do I contact support?
Support is available by email only. We do not offer a phone number, live chat, or on-call support teams. For technical issues or billing inquiries, please send an email to our support address. We aim to respond promptly, but please allow time for a detailed review of your request.
Is there a phone number?
No. We do not have a phone number. All communication is handled via email to maintain a clear, documented support trail. This approach allows us to manage support efficiently without the overhead of call centers, keeping our operational costs low and our API pricing competitive for indie developers.
Do you have an SLA?
No. We do not offer an SLA or uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue. While we strive for reliability, there is no enterprise contract or guaranteed response time.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, despite our endpoint compatibility. Our API uses the same request shape as the OpenAI speech endpoint, allowing you to use the official OpenAI SDKs by changing the base_url. However, we are an independent provider with our own keys, pricing, and voice models.
How are voices generated?
Voices are generated using a cloud text-to-speech API. You send text via a POST request, and we return an audio file. Requests are processed one after another, so under load a request may wait in a queue. We support speeds from 0.25x to 4.0x, allowing you to adjust pacing for different NPC personalities and scenes.
Is the audio watermarked?
Yes. Every generated file carries an inaudible watermark that marks it as synthetic speech. This helps identify AI-generated audio in your game assets. The watermark is embedded in the audio file itself, ensuring that even if the file is shared, its synthetic origin remains detectable by compatible tools.
Do you store audio files?
No. Generated audio is returned in the response and not stored by us. We keep request metadata (time, characters, status) for billing purposes only. Your audio files are delivered directly to your application, and we do not retain copies of the generated speech, ensuring your game assets remain yours.
What is the data retention policy?
Request metadata, including time, characters, and status, is kept for billing purposes. Input text is used only to produce audio and is not stored long-term. We do not retain the generated audio files. This minimal retention policy ensures that your data is used solely for delivering the service and processing payments.
Can I sue for voice rights?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. We do not offer custom voice cloning. Rights depend on the underlying license; consult legal advice for commercial use.
Do you offer refunds?
Failed requests are free: if synthesis fails, the charge is returned in full. For other cases, we do not offer automatic refunds. Since audio is generated on demand, refunds are handled on a case-by-case basis. Please contact support via email if you encounter a specific issue with a charge.
Is the team large?
We are an independent storefront, so our team size is not publicly disclosed. We operate efficiently with a focus on API reliability and developer experience. Our structure allows for quick decision-making and direct support, without the bureaucracy of a large corporation. We prioritize engineering quality over marketing scale.
Where are you located?
Our location is not specified. We do not have a physical office open to visitors. Our operations are managed remotely, allowing us to serve customers worldwide without geographic constraints on our team or servers.
Do you have investors?
EchoQuest operates as an independent business, funded through API usage and top-ups. We are not backed by venture capital or public markets, which allows us to maintain focus on developer needs rather than shareholder demands. Our pricing and features are driven by operational costs and value.
Are you open source?
No. Our API and models are proprietary. We do not offer open-source versions of our TTS engine. You interact with us via a REST API, but the underlying code and voice models are not publicly available. This allows us to maintain control over quality and licensing, ensuring consistent performance for all users.
Can I hire you?
We are a product company, not a service agency. We do not offer custom development or consulting services. You can use our API to integrate TTS into your game, but we do not build custom solutions for individual clients. If you need a tailored workflow, you will need to implement it using our documentation.
Do you have a blog?
We do not have a blog. Updates and announcements are shared via our documentation and support channels. We prefer direct communication through email and API status updates. This keeps our information concise and relevant for developers who need technical details rather than marketing content. Check our docs for the latest API changes.
Are you hiring?
We do not publicly list job openings. As an independent storefront, our hiring needs are not fixed. If we are looking for talent, we will reach out directly or update our contact page. We value engineering excellence and developer empathy, so if you are interested, keep an eye on our communication channels.
Who We Are
EchoQuest is an independent storefront for a single text-to-speech API, built specifically for freelance game developers who need reliable NPC dialogue generation without vendor lock-in. We provide a straightforward API endpoint that integrates into your existing audio pipeline with minimal overhead, keeping the focus on your game’s production rather than platform complexities.
Independent storefront
We operate as a standalone provider for this TTS API, meaning our business model is directly tied to your usage rather than a parent corporation’s broader ecosystem. This independence allows us to keep pricing transparent and integration simple, without the bloat of enterprise layers or unrelated product lines.
Focus on game audio
We understand that audio is a critical component of immersion, and our API is designed to handle the character limits and format requirements typical in game engines.
Engineer-led team
Built by engineers for engineers, our documentation and API design reflect practical development workflows. We prioritize clear endpoints, straightforward authentication, and predictable character limits, ensuring that you can integrate our speech generation into your build process with minimal overhead.
Voice Licensing
Our voice presets are built on high-quality, licensed recordings sourced from the LibriVox project. This ensures that every NPC line you generate rests on a solid legal foundation, allowing you to integrate voice assets into your game projects with confidence.
LibriTTS-R (CC BY 4.0)
We utilize the LibriTTS-R dataset, which is licensed under CC BY 4.0.
LibriVox public domain
The core audio material originates from LibriVox, a repository of public domain audiobook readings. These texts are free of copyright restrictions, providing a vast library of natural speech patterns that we convert into our eight distinct voice presets.
Licensed recordings
Every generated file carries an inaudible watermark marking it as synthetic speech. This distinguishes our API output from raw LibriVox recordings, ensuring clear provenance for your game’s audio pipeline without requiring manual attribution for each voice clip.
Data Policy
We treat your game dialogue data with strict privacy. Input text is used exclusively to generate the audio file and is not added to our training datasets. This ensures your unique NPC lines remain proprietary and do not influence future model behavior.
Generated audio is returned directly in the API response. We do not store the audio files long-term, meaning your voice assets are ephemeral by default unless you save them to your own game build.
Input not used for training
Your text inputs are processed solely for synthesis. We do not use this data to train or improve our TTS models, keeping your narrative content distinct from our engineering data.
Audio returned in response
The synthesized audio file is delivered immediately in the HTTP response. You retain full control over where this file is stored within your project pipeline.
No long-term storage
We do not retain the generated audio files after delivery. Only request metadata (time, characters, status) is kept for billing purposes, ensuring minimal data footprint.
Support
We keep our support structure simple and direct. When you need help with integration or billing, our primary channel is email.
Email support only
All support tickets are handled via email. This allows us to maintain a clear history of your issue and provide detailed, code-level assistance when needed. You can reach us at the address listed in our contact section.
No live chat
We do not offer live chat. This decision reduces overhead and ensures that every conversation receives focused attention from a team member who understands the API details.
No phone number
There is no phone support. For most game developers, asynchronous communication via email is more efficient for sharing logs, code snippets, and error messages. This approach keeps our team focused on solving technical problems rather than managing call schedules.

Limitations
We operate as an independent storefront without the infrastructure backing of a large enterprise. Our focus remains on providing a reliable, straightforward API for freelance game developers rather than maintaining complex operational guarantees.
No SLA or uptime guarantee
We do not publish a formal Service Level Agreement or promise a specific percentage of uptime. While we strive for consistent performance, request queues may form under load, and availability can vary.
No enterprise contract
Our service is designed for individual freelancers and small teams. We do not offer custom enterprise contracts, dedicated support lines, or negotiated terms for large-scale deployments.
No certifications
We do not hold specific industry certifications such as SOC 2, HIPAA, or GDPR certificates. Our data policy is simple: input text is used only for synthesis and not for training.
Contact
EchoQuest is an independent storefront built for freelance game developers. We focus on providing a reliable TTS API that integrates easily into your existing audio workflow, keeping things engineer-friendly and straightforward.
Our team is small and engineer-led, ensuring we understand the specific needs of NPC dialogue generation. We prioritize clear communication and practical solutions over corporate bureaucracy.
Email us for inquiries
We offer support strictly via email. There is no live chat widget and no phone number to call. This allows our small team to provide thoughtful, detailed responses to your technical questions without the noise of real-time interruptions.
Check documentation
Most integration questions are answered in our technical docs. Before emailing, please review the endpoint details, voice presets, and rate limits. Our documentation is updated regularly to reflect the current API behavior and character limits.
Read FAQ
The FAQ covers common concerns regarding character counting, voice selection, and payment methods. It explains how our TRC-20 top-ups work and clarifies our data usage policies.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
