VocalWave TTS API: 8 Preset Voices for Streamers

By VocalWave editorial team · Updated 2026-11-18

VocalWave is a text-to-speech API built for streamers and VTubers who need consistent, license-safe voice assets without the overhead of custom training. You get 8 preset voices—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—capable of speaking 23 languages with transparent, character-based pricing. This page outlines how to integrate these voices into your streaming workflow using our OpenAI-compatible endpoint.

We handle the infrastructure so you can focus on content. Input text is used only for generation, not for training, and generated audio is returned in the response without being stored. With no monthly subscriptions and USDT (TRC-20) payments, you pay only for what you use. Explore the voice list, technical specs, and pricing below to start generating audio for your streams.

VocalWave TTS API: 8 Preset Voices for Streamers

Frequently asked questions

Is VocalWave a voice cloning app?

No. VocalWave provides eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. We do not offer custom voice cloning, voice design, or the ability to upload and train your own voice. Each generated file includes an inaudible watermark marking it as synthetic speech.

Can I clone my own voice for streaming?

No. We do not offer custom voice cloning or uploading your own voice. You must choose from our eight preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion. These are based on licensed recordings and available immediately via the API.

Which voice is best for VTuber content?

Q: Which voice is suitable for VTuber content? A: Choice depends on your avatar’s persona. For energetic, promo-style streams, use Felix. For friendly, conversational interaction, use Milo. For soft, storytelling moments, Luna is suitable. All eight voices support 23 languages, allowing you to match the voice to the content’s tone.

How do I pay with USDT?

Top up your balance using USDT on the TRON network (TRC-20). The minimum deposit is $5. Credits are added automatically within minutes after the transfer. We do not accept cards, PayPal, or subscriptions. Your balance does not expire.

What is the character limit per request?

Each API request accepts up to 4,096 characters of input text. Spaces and punctuation count toward this limit. For longer texts, split the content into chunks of 4,096 characters and join the resulting audio files programmatically.

Are the voices based on real people?

A: Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. While derived from real recordings, they are processed into eight distinct preset voices available via the API.

Do you store my generated audio?

No. Generated audio is returned in the response and not stored on our servers. Input text is used only to produce the audio and is not used for training. We retain request metadata (time, characters, status) for billing purposes.

Is there a free trial?

Yes. Signing in with Google provides $0.50 of credit (about 50,000 characters), valid for 7 days. Accounts created with email and password start without trial credit. Failed requests are free, so you can test without charge.

What happens if a request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This allows you to retry or adjust parameters without losing your balance. Typical speed is roughly real time for long texts.

Do you support SSML?

No. VocalWave does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control speech by adjusting the speed parameter (0.25–4.0) and selecting the appropriate voice preset. Emotion tags and SSML markup are not available.

Can I use the audio commercially?

Yes. The underlying recordings are from LibriTTS-R (CC BY 4.0) and LibriVox public domain. You can use the generated audio for streaming, video production, and other commercial projects without additional licensing overhead or custom training requirements.

How do I handle long texts?

Split your text into parts of up to 4,096 characters. Send each part as a separate API request. Then, join the resulting audio files. Requests are processed sequentially, so under load, a request may wait in a queue.

What is the API rate limit?

The limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. You can issue a new key at any time, which invalidates the old one immediately.

Do you offer phone support?

No. We do not offer a phone number or live chat. Support is provided via email only. There is no SLA or uptime guarantee. For technical issues, contact us through the email address provided on the contact page.

First request

curl

curl https://api.playbet177.com/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Why Streamers Choose TTS

Sound wave illustration for: Why Streamers Choose TTS

Streamers need audio assets that sound consistent across thousands of clips. VocalWave provides eight preset voices, ensuring your VTuber or stream persona never sounds tired or varied between sessions.

Consistent Brand Voice

Consistent Brand Voice

Recording fatigue is real. A single recording session can yield only so many unique variations before the voice sounds strained. With VocalWave, you generate fresh lines instantly without vocal strain, keeping your content delivery steady and professional.

No Recording Fatigue

Stop worrying about background noise or mic settings. Generate dialogue, reactions, and narrations directly from text. This allows you to focus on streaming or video editing while the API handles the voice synthesis.

Instant Content Generation

Short phrases take a few seconds; long texts generate at roughly real-time speed. Split up to 4096 characters per request and join the audio files seamlessly. This workflow lets you produce voiceovers for videos or live chat responses without waiting for a studio.

Available Voices

Sound wave illustration for: Available Voices

VocalWave provides eight distinct voice presets engineered for consistent branding in streaming and video production. Each voice is derived from licensed recordings, ensuring your audio assets remain license-safe without the overhead of custom training or voice design processes.

Female Presets: Aria, Nova, Luna, Sage

Aria delivers a warm, clear narration ideal for commentary. Nova offers a bright, upbeat tone suitable for high-energy segments. Luna provides a soft, storytelling voice for narrative content, while Sage presents a calm, instructional tone perfect for tutorials or guides.

Male Presets: Felix, Milo, Atlas, Orion

Felix brings an energetic, promo-ready voice for dynamic highlights. Milo offers a friendly, conversational style for engaging interaction. Atlas provides a neutral, news-like delivery, and Orion delivers a deep, documentary-style voice for serious or cinematic contexts.

Voice Characteristics Explained

All eight voices support 23 languages, allowing any voice to speak any supported language. If the language field is omitted, the system guesses the language from the script (defaulting to English for Latin text). You can explicitly set the language via ISO code to ensure accuracy.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional
  • Felix: Energetic, promo
  • Milo: Friendly, conversational

Supported Languages

Sound wave illustration for: Supported Languages

VocalWave supports 23 languages, covering major markets for global content creators. Our engine handles diverse scripts without requiring separate voice models, ensuring consistent audio quality across your stream’s multilingual segments.

23 Languages Supported

We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If a language is not listed, it is not supported.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Automatic Language Detection

The API guesses the language from the script’s characters. Latin text defaults to English. This works for most standard inputs without extra configuration.

Manual Language Override

For non-English Latin-script text, explicitly set the language field. This prevents misidentification and ensures the correct voice rendering.

Pricing & Payments

Sound wave illustration for: Pricing & Payments

VocalWave charges $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Failed requests are refunded in full, ensuring you only pay for successful synthesis. The rate is transparent and scales linearly with usage.

Payments are processed exclusively via USDT on the TRON network (TRC-20). There are no credit cards, PayPal options, or invoice-based billing. Transfers are credited automatically within minutes, with a minimum top-up of $5. Your balance never expires.

Pay Per Character

The cost is fixed at $10 per million characters. You pay only for what you generate, with no hidden fees for high-quality audio or specific voices.

  • $0.01 per 1,000 characters
  • Failed requests are free
  • Spaces and punctuation count

USDT (TRC-20) Only

Top-ups are made using USDT on the TRON network. The minimum deposit is $5. Funds appear in your account within minutes of the blockchain confirmation.

  • USDT (TRC-20) only
  • Minimum $5 top-up
  • Automatic credit within minutes

No Monthly Subscriptions

There are no recurring plans, seats, or minimum spend requirements. Start with a $0.50 free trial (7 days) via Google sign-in, then pay only as you stream.

Technical Specs

Sound wave illustration for: Technical Specs

VocalWave’s API mirrors the OpenAI speech endpoint structure, allowing you to reuse existing client libraries by simply updating the base_url to https://api.playbet177.com/v1. Authentication uses a standard Bearer token, ensuring seamless integration into your current streaming or content automation pipelines without requiring a custom SDK download.

Generate audio in MP3, WAV, OPUS, FLAC, or PCM formats to suit your specific encoding needs. Whether you need lightweight files for live overlays or lossless masters for video editing, the API handles the conversion instantly. You control the output quality directly through the response_format parameter in your JSON payload.

OpenAI Compatible SDK

Use the official OpenAI Python or Node.js SDKs by pointing them to our base URL. This compatibility means you can leverage existing community wrappers and tools designed for TTS workflows without rewriting your integration logic.

  • Standard JSON request body
  • Compatible with OpenAI SDK clients
  • Simple base_url configuration change

Multiple Audio Formats

Choose between MP3, WAV, OPUS, FLAC, or PCM based on your storage and latency requirements. OPUS offers efficient compression, while FLAC provides lossless quality for archival.

  • MP3: Universal compatibility
  • WAV: Standard uncompressed audio
  • OPUS: Efficient streaming compression
  • FLAC: Lossless quality
  • PCM: Raw uncompressed data

Rate Limits Explained

New accounts start with a limit of 10 requests per minute. After your first top-up, this increases to 60 requests per minute per API key. Requests are processed sequentially, so high-volume batches may queue briefly.

Keep your text under 4,096 characters per request to avoid splitting overhead. For longer scripts, split the text in your application logic and concatenate the resulting audio files.

  • Standard limit: 60 req/min
  • Initial limit: 10 req/min
  • Sequential processing queue
Technical Specs

Use Cases

Sound wave illustration for: Use Cases

VocalWave provides consistent, license-safe voice assets for content creators who need reliable audio without the overhead of custom training or recording fatigue. Our 8 preset voices ensure your brand sound remains uniform across all streams and videos.

VTuber Chat Responses

Generate instant chat interactions or alerts without breaking your stream flow. Use voices like Felix for energetic announcements or Milo for friendly conversational replies, keeping your audience engaged with consistent audio quality.

  • Real-time alert integration
  • Consistent character voice
  • No recording fatigue

Stream Intro/Outro Audio

Create unique intro and outro segments using presets like Aria or Orion. With character-based pricing, you can produce unlimited variations of your stream branding without monthly subscription fees or minimum spend requirements.

  • Unique branding audio
  • No monthly fees
  • Instant generation

Video Voiceovers

Produce voiceovers for YouTube or Twitch VODs using our TTS-1 engine. Supports multiple formats including MP3 and WAV, ensuring compatibility with any video editing software while maintaining clear, natural speech.

  • Multiple audio formats
  • High clarity
  • Easy integration

Data & Privacy

Sound wave illustration for: Data & Privacy

Your input text is processed exclusively to generate the audio file and is never used for model training. We do not retain the generated audio files; they are delivered in the response and not stored on our servers for later use or analysis.

No Training on Input

The text you send to the API is used solely for synthesis. Once the audio is generated and returned, the original text is not kept for retraining or improving our voice models. This ensures your script content remains private to your workflow.

No Audio Storage

Generated audio files are returned directly in the API response and are not stored on our infrastructure. You own the resulting audio immediately, and we do not host or archive your voice assets after delivery.

Metadata for Billing

We retain request metadata—including timestamp, character count, and status—to accurately calculate your usage and charge your balance. This data is kept strictly for billing purposes and does not include the content of your spoken text.

Getting Started

Sound wave illustration for: Getting Started

Create your account in seconds via Google sign-in on the /get-api-key/ page to access the dashboard instantly. Your account is tied to the playbet177.com domain, ensuring a straightforward setup without complex enterprise onboarding. Upon registration, you receive an active API key and a $0.50 trial credit valid for 7 days, covering approximately 50,000 characters for immediate testing.

Navigate to the dashboard to view your key, balance, and usage statistics. The interface provides a ready-to-use cURL example, allowing you to verify connectivity before integrating the API into your streaming software or video production pipeline. No credit card or subscription is required to begin.

Sign Up with Google

Register instantly using your Google account on the /get-api-key/ page. This method assigns a unique API key and grants immediate access to the $0.50 trial credit, valid for 7 days. Accounts created via email/password do not receive this trial credit.

Get Your API Key

Your API key is displayed prominently on the dashboard alongside your current balance and character usage. Use this key in the Authorization header: Authorization: Bearer tts-.... You can generate a new key at any time; the previous key becomes invalid immediately.

  • One active key per account
  • New keys invalidate old ones instantly
  • Visible in dashboard with usage stats

First Request Example

Test the API with a simple cURL command. Replace YOUR_API_KEY with your actual key. This request generates a 5-second audio clip using the 'nova' voice.

```bash curl -X POST https://api.playbet177.com/v1/audio/speech \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Hello streamers, welcome back.", "voice": "nova", "response_format": "mp3"}' ```

The response returns the audio file directly. For longer texts, split input into 4096-character chunks and join the resulting audio files.

FAQ Overview

Sound wave illustration for: FAQ Overview

This API uses eight fixed preset voices derived from licensed recordings, not custom voice cloning. Each generated file includes an inaudible watermark to mark it as synthetic speech.

You cannot clone your own voice or upload a custom recording. The voices are static presets; there is no voice design or emotion tagging available.

Is this voice cloning?

No. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. They are fixed presets, not learned models of a specific person's unique voice.

  • Uses licensed, public-domain source material
  • Generates synthetic speech with inaudible watermarks

Can I clone my own voice?

No custom voice cloning is offered. You cannot upload your own voice samples to create a new preset. The eight available voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are the only options.

  • No uploading of voice samples
  • No custom voice creation

What formats are supported?

The API supports MP3, WAV, Opus, FLAC, and PCM. You can specify the response_format in your request. There is no streaming or WebSocket support; you receive the full audio file after processing.

  • MP3, WAV, Opus, FLAC, PCM

How fast is generation?

Generation takes roughly real-time speed (25 characters per second) for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so high load can cause queuing delays.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Your first request works instantly, with no waiting for model training or quality assurance checks.

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. W3C WAI: making audio and video accessible
  3. LibriVox public-domain audiobooks
  4. Tether (USDT)
  5. Node.js documentation
  6. TRON developer hub: TRC-20
  7. openai-node on GitHub
  8. MDN: Web Speech API
  9. LibriTTS-R corpus (OpenSLR 141)
  10. FFmpeg documentation
  11. LibriTTS-R paper (arXiv 2305.18802)
  12. Creative Commons Attribution 4.0

More on this site