Cloud TTS API: 8 Licensed Voices, 23 Languages, $0.01/1k Chars

By EchoVocal editorial team · Updated 2026-11-18

This page explains how EchoVocal audits text-to-speech APIs for VTuber and indie developer workflows. We evaluate voice licensing, consent ethics, and preset quality to help you choose synthetic voices that respect creator rights while delivering broadcast-ready audio for your streams.

You will find our editorial focus, data policies, and honest reviews of the EchoVocal API. If you need transparent insights into 8 licensed voices, 23 languages, and fair pricing, this is the place to verify the product’s fit for your specific content creation needs.

Cloud TTS API: 8 Licensed Voices, 23 Languages, $0.01/1k Chars

Frequently asked questions

Who runs this site?

EchoVocal is an independent storefront for the EchoVocal text-to-speech API. We operate as a separate entity, not affiliated with OpenAI, ElevenLabs, or other major brands. Our team audits TTS APIs specifically for VTuber and streamer workflows, helping indie developers choose synthetic voices that respect creator rights while delivering broadcast-ready audio.

What is your mission?

We audit TTS APIs through the lens of VTuber and streamer workflows, focusing on voice cloning ethics, consent, and preset voice quality. Our reviews help indie developers choose synthetic voices that respect creator rights while delivering broadcast-ready audio. We prioritize honest, specific data over hype to assist your technical decisions.

How are voices licensed?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. Every generated audio file carries an inaudible watermark that marks it as synthetic speech, ensuring transparency about the origin and nature of the synthetic audio produced by our API.

Do you use my data for training?

No. Input text is used only to produce the audio and is not used for training. We do not use your content to improve our models or for any other purposes beyond generating the requested audio file.

Do you store audio files?

No. Generated audio is returned in the response and not stored on our servers. We keep request metadata, such as time, characters, and status, strictly for billing purposes.

How can I contact you?

Support is available by email only. We do not offer phone support or live chat. You can reach our team via the contact page or the email link provided in the footer. Please include your API key and details about your issue for faster assistance.

Do you have a phone number?

No, we do not have a phone number. All support interactions are conducted via email. This allows us to maintain detailed records of your technical issues, ensuring consistent and documented support for indie developers and VTuber streamers using our text-to-speech API.

Is there live chat support?

No, there is no live chat support. We rely entirely on email support to handle inquiries. This approach ensures that every question is documented and can be referenced later if needed, providing a reliable audit trail for technical issues regarding your API keys, billing, or voice generation.

Who We Are

Sound wave illustration for: Who We Are

We are an editorial team auditing text-to-speech APIs through the specific lens of VTuber and streamer workflows. Our reviews help indie developers choose synthetic voices that respect creator rights while delivering broadcast-ready audio.

Editorial team focus

Editorial team focus

We evaluate technical specifications and ethical implications simultaneously. Our analysis prioritizes voice cloning ethics, consent models, and the actual quality of preset voices for live content.

VTuber and streamer expertise

VTuber and streamer expertise

Our team understands the constraints of live streaming environments. We test audio clarity and voice consistency under load to ensure reliable performance for batch workflows.

Indie developer audience

Indie developer audience

We provide concrete data for developers building interactive experiences. Our guides focus on practical integration steps, pricing transparency, and API reliability for small-scale projects.

Our Mission

Sound wave illustration for: Our Mission

We audit TTS APIs through the lens of VTuber and streamer workflows, helping indie developers choose synthetic voices that respect creator rights while delivering broadcast-ready audio. Our reviews focus on concrete facts, not hype, ensuring you understand exactly what you are buying.

Honest reviews

Honest reviews

We test every feature against real workflow needs. Our reviews are based on actual API usage, not marketing decks. We highlight limitations like the lack of streaming or SSML so you can plan your integration accurately.

  • Real-world workflow focus
  • Concrete statistics, not hype
  • Limitations clearly stated

Ethical voice usage

Every generated file carries an inaudible watermark marking it as synthetic speech. We prioritize licensed recordings from LibriVox public-domain audiobook readings, ensuring clear provenance for your commercial or non-commercial projects.

  • Inaudible synthetic watermark
  • LibriVox public-domain sources
  • Clear commercial provenance

Transparency in AI

We do not hide behind black-box algorithms. Our pricing is straightforward: $0.01 per 1,000 characters. Failed requests are free, and balance never expires. We explain exactly how your text becomes audio.

  • Straightforward pricing
  • Free failed requests
  • Clear process explanation

Voice Licensing

Sound wave illustration for: Voice Licensing

EchoVocal audits synthetic voices through the lens of VTuber and streamer workflows, ensuring that every preset voice used in our API is properly licensed for commercial use. We focus on transparency so indie developers can confidently integrate audio into their broadcasts without legal ambiguity.

LibriTTS-R license

Our eight voice presets are derived from the LibriTTS-R dataset, which provides a standardized subset of the LibriSpeech corpus. This dataset is specifically curated for text-to-speech research, ensuring consistent quality across all available voices.

LibriVox sources

The underlying audio recordings originate from LibriVox, a platform for public-domain audiobook readings. Each voice preset is based on these licensed recordings, preserving the natural intonation and clarity required for broadcast-ready synthetic speech in our API.

CC BY 4.0 details

LibriTTS-R is released under the Creative Commons Attribution 4.0 International license. This allows us to build and distribute our TTS engine while respecting the original creators. We ensure that all generated audio files meet the attribution requirements for commercial use.

Data Policy

Sound wave illustration for: Data Policy

We process input text solely to generate the requested audio file. Your words are not repurposed for other products or services.

Input text usage

When you send a request, the text is converted into audio and returned in the response. We do not store the generated audio files.

No training on data

Your input text is not used to train our models. Each synthesis is independent, ensuring your content remains distinct from our training datasets.

Metadata retention

We retain request metadata, including timestamp, character count, and status, strictly for billing and usage tracking purposes.

Data Policy

Product Limitations

Sound wave illustration for: Product Limitations

We prioritize transparency about what the EchoVocal API does not do. Understanding these boundaries helps VTubers and indie developers select the right tool for their specific broadcast workflows without unexpected gaps in functionality.

No custom cloning

The API uses eight fixed presets based on licensed recordings. It does not offer custom voice cloning or the ability to upload and train a new voice from your own samples.

No SSML support

Requests accept plain text strings only. There is no support for SSML tags to control pause durations, pitch changes, or emphasis within the synthesized audio output.

No streaming

Audio is generated as a complete file upon request completion. The endpoint does not support WebSocket or chunked streaming, meaning partial audio chunks are not available during synthesis.

Contact Us

Sound wave illustration for: Contact Us

We are a small editorial team, so we handle every inquiry personally. All communication goes through our support email, ensuring your question reaches the right person without automated filters or complex menus.

Since we do not maintain a call center or live chat infrastructure, you will always speak with a human who understands the technical nuances of our API.

Email support only

Send your technical questions, billing inquiries, or feedback to [email protected]. This is the only channel for customer service, keeping our operations lean and focused on product development.

No phone or live chat

We do not offer phone support or real-time live chat widgets. This allows us to maintain detailed, searchable records of every conversation, which helps us improve the API and documentation for everyone.

Response times

We aim to respond to all emails within 24 hours during business days. Complex technical issues may take slightly longer, but we prioritize clarity and accuracy over speed.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. VTubers and streamers are turning our indie games into viral sensations, driving massive engagement through their unique and entertaining content.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. OpenAI API reference: create speech
  3. LibriTTS-R paper (arXiv 2305.18802)
  4. FFmpeg documentation
  5. curl documentation
  6. openai-python on GitHub
  7. Node.js documentation
  8. Python documentation
  9. openai-node on GitHub
  10. Creative Commons Attribution 4.0
  11. Tether (USDT)
  12. MDN: Web Speech API

More on this site