Frequently asked questions
Can I use the generated audio for my Twitch VODs?
Yes. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. You can use the resulting MP3, WAV, Opus, FLAC, or PCM files in your Twitch VODs without restriction.
Which voice is best for a VTuber avatar?
No single voice is objectively best for every VTuber avatar. Choose based on your character’s personality: Aria (warm), Nova (bright), Luna (soft), Sage (calm), Felix (energetic), Milo (friendly), Atlas (neutral), or Orion (deep). Each preset suits different streaming styles, so select the tone that matches your avatar’s vibe. Since any voice can speak any supported language, pick the preset that best fits your stream’s atmosphere.
Do the voices sound robotic?
The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They are natural-sounding synthetic speech. Every generated file carries an inaudible watermark that marks it as synthetic, but the audio quality is designed to be clear and suitable for streaming content.
Can I change the speed of the speech?
Yes. You can adjust the speed parameter in the API request between 0.25 and 4.0. This allows you to speed up emote reactions or slow down dialogue for better clarity in your VTuber streams without needing external audio editing tools.
Does the API support Japanese text?
Yes. Japanese is one of the 23 supported languages. You can use any of the 8 voice presets to speak Japanese. If you do not set the language field, the system guesses it from the script, but you should explicitly set it for non-English Latin text.
What happens if the generation fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You will not be billed for characters processed in a failed request, ensuring you only pay for successfully generated audio files.
Can I use the audio in YouTube videos?
Yes. The input text is used only to produce the audio and is not used for training. The generated audio is returned in the response and not stored. You can use the audio files in your YouTube videos without additional licensing constraints from this API.
Do I need to credit the voice actors?
The API does not require you to credit individual voice actors. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. While the underlying source data carries specific licenses, our service does not mandate attribution to the original narrators for your streams or VODs.
Is there a limit on video length?
There is no limit on video length. You can split longer texts into parts of up to 4096 characters and join the audio files. This allows you to generate audio for videos of any duration by chaining multiple API requests together.
Can I download MP3 files directly?
Yes. You can request the response_format as mp3, wav, opus, flac, or pcm. The API returns the audio file directly in the response, allowing you to save it locally or stream it directly to your VTuber overlay software.
Do you offer voice cloning for streamers?
No. We do not offer custom voice cloning, uploading your own voice, or voice design. The service provides eight preset voices based on licensed recordings. You cannot create a unique voice clone of yourself or another person through this API.
What is the character limit per request?
The input field accepts up to 4096 characters per request. Spaces and punctuation count as characters. For longer texts, you should split the content into chunks of 4096 characters or less and join the resulting audio files.
Can I mix different voices in one video?
Yes. You can make separate API requests for each voice preset (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) and combine the resulting audio files. This allows you to create dynamic scenes with different characters in your VTuber videos.
How long does it take to generate audio?
Typical speed is roughly real time, about 25 characters of text per second of generation. Short phrases take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue before processing begins.
First request
curl
curl https://api.playb77.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.mp3Generate Speech for VTuber Avatars
VocalFlow generates clear, licensed speech for VTuber avatars and stream overlays. Use the API or online tool to create audio files for VODs, intros, and emote reactions without writing code. Send text and receive an audio file via a simple POST request.
Generation is not always instant. Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds to synthesize.
Instant VOD Voiceovers
Generate voiceovers for your VODs directly from your script. The API converts text up to 4096 characters into audio, which you can download and embed into your video editor.
Since requests are processed one after another, complex queues may cause slight delays. However, the process remains automated and requires no manual editing of the generated audio.
- Send text, receive audio file
- No manual editing required
- Sequential processing under load
Emote Reaction Sounds
Create custom reaction audio clips for your stream overlay. Choose from eight voice presets like Aria or Nova to match your avatar’s personality.
Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring clear attribution without affecting the listening experience for your audience.
Stream Intro Scripts
Convert your stream intro script into professional audio. Select a voice like Felix for energetic promos or Atlas for neutral news-style intros.
Use the speed control (0.25x–4.0x) to adjust pacing. For longer intros, split the text into parts of up to 4096 characters and join the resulting audio files.
Choose Your Voice Style
Select a voice preset that matches your stream’s vibe. Each preset is based on licensed recordings, ensuring clear and professional audio for your VODs and live overlays.
Warm Narrator (Aria)
Aria offers a warm, clear narrator style ideal for lore dumps, story intros, and character dialogue.
Bright Upbeat (Nova)
Nova delivers a bright, upbeat tone suitable for hype moments, quick updates, and energetic reactions.
Deep Documentary (Orion)
Orion provides a deep, documentary-style voice perfect for news updates, serious commentary, and segment transitions.

Technical Specs for Streamers
Generate audio in MP3, WAV, OPUS, FLAC, or PCM formats. MP3 is a supported format for efficient file sizes, while WAV provides lossless quality for editing. Choose the container that best fits your streaming software’s requirements without compromising on the synthetic audio data.
MP3 and WAV Formats
Select MP3 for compressed files that are easy to manage, or WAV for lossless fidelity. Both formats are fully supported for VODs and live overlays. The API returns the audio file directly in the response, allowing you to download or pipe it into your broadcast software immediately.
- Supported formats: mp3, wav, opus, flac, pcm
- Lossless WAV for high-quality editing
- Compressed MP3 for easy file management
Speed Control 0.25x–4.0x
Adjust the generation speed from 0.25x to 4.0x to match your stream’s pacing. This allows you to slow down narration for clarity or speed up emote reactions for quick timing. Requests are processed sequentially, so longer texts may take a few seconds to generate depending on queue load.
- Range: 0.25x to 4.0x
- Adjustable per request
- Ideal for matching VOD pacing
No SSML Needed
You do not need SSML tags to control the output. The API uses simple text input and voice presets to deliver clear speech. Focus on your script content rather than learning complex markup. The system handles pronunciation and intonation through the selected voice model, keeping your integration simple.
Supported Languages
Generate clear speech in any of the supported languages. The API supports 23 languages, allowing VTubers to create content for global audiences without needing separate voice models for each region.
English, Japanese, Korean
Support English, Japanese, Korean, and other major languages. Any voice preset can speak any of the supported languages. If the language is not specified, the system guesses it from the script, but setting it explicitly ensures accuracy for non-English Latin text.
Spanish, French, German
Create localized stream intros or VOD voiceovers in Spanish, French, German, and many others. The same engine powers all supported languages, ensuring consistent audio quality across your multilingual content library.
23 Languages Total
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Simple Pricing Model
The pricing structure is straightforward: $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full if synthesis fails.
$10 per Million Characters
You pay only for what you generate. The rate is $10 per 1 million characters. There are no hidden fees or variable costs based on voice quality or format.
No Monthly Subscriptions
There are no monthly plans, seats, or minimum spend requirements. You top up your balance when needed. Balances do not expire, and you can use funds whenever your stream schedule demands.
Free Trial Credit
Sign in with Google to receive $0.50 of free credit, valid for 7 days. This covers about 50,000 characters, enough to test voice styles for your VTuber avatar before committing to a top-up.

How It Works
Generate clear speech for your VTuber avatars or stream overlays in three simple steps. This workflow works for both the online tool and the API, letting you create VOD voiceovers, emote reactions, and intro scripts without writing code.
Type Your Script
Enter your text (up to 4,096 characters) into the input field. The system automatically splits longer texts into parts and joins the audio files. Requests are processed sequentially, so under load, a request may wait in a queue before generation begins.
Select Voice and Language
Choose from eight preset voices like Aria for warm narration or Orion for deep documentary tones. Select your language from 23 options or leave it blank for automatic detection. Adjust the speed between 0.25x and 4.0x to match your stream's pace.
Download Audio File
Once synthesis completes, download your audio file in MP3, WAV, OPUS, FLAC, or PCM format. Files are ready for immediate use in your broadcasting software, carrying an inaudible watermark that marks the speech as synthetic.
API for Developers
VocalFlow uses the same request shape as the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply changing the base_url to https://api.playb77.com/v1. This compatibility means you can integrate TTS into your existing workflows without learning a new library or parsing complex custom formats.
OpenAI SDK Compatible
You can use the standard OpenAI SDK for Python or Node.js. Just set the base URL to https://api.playb77.com/v1 and pass your tts-... API key. This eliminates the need for custom HTTP clients or manual JSON serialization for most common use cases.
Easy JSON Integration
Send a simple POST request to /v1/audio/speech with a JSON body. Include your model (tts-1 or tts-1-hd), input text, voice preset, and response_format. The API returns the audio file directly, making it easy to pipe into streaming software or save as VOD assets.
- Endpoint: POST https://api.playb77.com/v1/audio/speech
- Auth: Bearer tts-... key
- Formats: mp3, wav, opus, flac, pcm
Real-time Generation
Requests are processed sequentially. While generation is roughly real-time (approx. 25 characters per second), long scripts may queue. For live streaming, pre-generate intros or emotes to avoid latency. Short phrases take a few seconds to synthesize.
Licensing and Rights
Every voice in our library is based on licensed recordings sourced from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This foundation ensures that the underlying audio data is legally cleared for commercial use, allowing you to generate speech for VODs, intros, and emote reactions without worrying about copyright strikes on your stream content.
Licensed Recordings
The voice presets are built from specific, licensed recordings rather than raw, unprocessed data. This means the resulting synthetic speech inherits a clear licensing path, making it safe for use in both live streams and archived video content.
Public Domain Base
In addition to licensed material, we utilize recordings from LibriVox, which are in the public domain. This dual approach provides a robust legal foundation for your generated audio, ensuring that your stream overlays and VOD voiceovers remain compliant.
Synthetic Watermark
Every audio file generated through our API carries an inaudible watermark that marks it as synthetic speech. This transparent marker helps platforms and audiences identify AI-generated content, adding an extra layer of clarity to your stream's audio identity.

Support and Contact
We provide email support as our sole communication channel. We do not offer live chat or phone support, ensuring focused attention on your queries without the noise of real-time queues. All support requests are handled via email to maintain clear records and detailed responses.
Email Support Only
Send your questions or issues to our support email address. We respond to emails as quickly as possible, though no specific response time is guaranteed. This asynchronous approach allows us to provide thorough answers for technical and billing inquiries.
No Live Chat
Unlike some platforms, we do not maintain a live chat widget on this site. If you need immediate assistance, check the documentation first. For complex issues requiring context, email remains the most effective method for both you and our support team.
Documentation Available
For quick answers on API integration, voice selection, and pricing, visit our documentation page. It covers all technical details, including request formats and error codes. Most common VTuber streaming questions are addressed there before you need to reach out via email.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Create your own virtual persona with animated avatars and start streaming to your audience today.
23 languages
Any voice speaks any of these languages.
