Frequently asked questions
Is the French TTS natural enough for professional podcasts?
Yes. Our voices are based on licensed recordings from LibriVox public-domain audiobook readings, ensuring a natural sound. You can generate high-quality narration instantly using a simple API. The audio is suitable for professional podcasts without needing expensive studio time.
Which voices sound best for storytelling?
Luna is described as soft and storytelling. Sage is ideal for calm, instructional content. Both voices support French and other languages. You can adjust speed between 0.25 and 4.0 to match your pacing preferences for engaging podcast episodes.
Can I use the generated audio commercially?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can use the generated audio for your podcasts. Each file carries an inaudible watermark marking it as synthetic speech.
How many characters can I send in one request?
You can send up to 4096 characters per request. For longer texts, split them into parts of this limit and join the audio files. This ensures efficient processing and maintains the quality of your generated narration.
Do I need to install special software to use the API?
No. You can use the official OpenAI SDKs by changing the base_url to https://api.playgb168.com/v1. Alternatively, send a POST request to the /v1/audio/speech endpoint. No special software is required to integrate the API.
What happens if my internet cuts out during generation?
The API processes requests sequentially. If a request fails, the charge is returned in full. You can retry the request or split your text into smaller parts. Failed requests are free, so you only pay for successful generations.
Is there a limit to how many episodes I can generate?
There is no limit to the number of episodes. You pay $0.01 per 1,000 characters. You can generate as many episodes as your balance allows. There are no monthly plans, seats, or minimum spend requirements for your account.
Can I change the speed of the narration?
Yes. You can adjust the speed between 0.25 and 4.0 using the speed parameter. This allows you to customize the pacing of your narration. The default speed is 1.0, but you can slow it down or speed it up.
Do you support accents other than standard French?
We support French. Any voice can speak any of the 23 supported languages, including French. If you need a specific accent, you may need to experiment with different voices like Luna or Sage.
How is the character count calculated?
Spaces and punctuation count as characters. The price is $0.01 per 1,000 characters. This includes all input text sent to the API. You can track your usage and balance directly on the /get-api-key/ page of your account.
Can I mix different voices in one episode?
The API generates audio for one voice per request. To mix voices, generate separate audio files for each voice and join them. You can use voices like Aria, Nova, Luna, or Felix to create diverse podcast episodes.
What formats are best for podcast hosting platforms?
You can choose from mp3, wav, opus, flac, or pcm. MP3 is widely supported by most podcast hosting platforms. Select the response_format parameter in your request to specify your preferred audio format for the generated speech.
Do I get a refund if the audio generation fails?
Yes. If synthesis fails, the charge is returned in full. Failed requests are free. You only pay for successful generations. You can monitor your usage and balance on the /get-api-key/ page to track any refunds or charges.
How long does it take to generate a 5-minute episode?
Typical speed is roughly real time, about 25 characters per second. A 5-minute episode may take several minutes to generate. Requests are processed sequentially, so under load, a request may wait in a queue before processing.
First request
curl
curl https://api.playgb168.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.mp3Why Podcasters Choose Our API
Our API ensures your characters sound consistent across episodes, maintaining the same tone and pace without the need for re-recording. This consistency builds trust with your audience, keeping them engaged from intro to outro.
With our API, you can turn your script into audio instantly. No more waiting for studio slots or coordinating schedules. Just send your text, and receive high-quality narration ready for your podcast.
Forget the hassle of booking studios and engineers. Our API lets you generate professional-grade narration on demand, freeing you to focus on content creation rather than production logistics.
Consistent Character Voice
Maintain character consistency across episodes. Aria’s warm narration or Nova’s upbeat tone remains uniform, ensuring your listeners recognize your show’s unique voice immediately.
Whether it’s a deep documentary style with Orion or a friendly conversational tone with Milo, each voice preset delivers a reliable, recognizable sound that aligns with your brand identity.
- 8 distinct voice presets for diverse characters
- Consistent tone across all episodes
- No need for re-recording for minor script changes
Instant Script-to-Audio
Convert your written script into audio files in seconds. Our API processes requests, allowing you to iterate on your content.
Ideal for last-minute script updates or adding new segments to your episode. Simply send the text, and receive the audio file ready for editing and publishing.
- Fast processing times
- Immediate audio file delivery
- Easy integration with your workflow
No Studio Booking Needed
Eliminate the need for scheduling studio time and hiring voice actors. Our API provides on-demand narration, reducing production costs and increasing flexibility.
Generate as many narration tracks as needed without the logistical headaches of traditional recording studios. Perfect for indie podcasters and small teams.
- On-demand narration generation
- Reduced production costs
- Increased flexibility for content updates
Premium Voices for Your Show
Choosing the right voice defines your podcast’s personality. Our curated catalog ensures every episode sounds professional, whether you need a warm storyteller or an energetic host. Each voice is built from licensed recordings, guaranteeing a distinct and natural tone for your content.
Selecting a preset is straightforward. Our voices handle French and 22 other languages, allowing you to maintain consistent character voices across episodes.
Aria: Warm Narrator
Aria delivers a clear, warm tone ideal for narrative-driven podcasts. Her voice brings depth to long-form storytelling, making her perfect for audiobook-style segments or historical deep dives.
She excels at holding listener attention through nuanced pacing. Use Aria for chapters where emotional resonance matters more than high energy.
- Ideal for narrative arcs
- Clear enunciation
- Warm, inviting tone
Nova: Upbeat Host
Nova brings bright, upbeat energy to your intro segments or daily updates. Her conversational style feels like a friend talking directly to your audience, keeping engagement high from the first second.
She handles casual scripts with ease. Nova is best for show introductions, quick tips, or lively discussion prompts where you want to sound approachable and energetic.
- High energy
- Casual and friendly
- Great for intros
Sage: Calm Instructor
Sage offers a calm, instructional tone perfect for educational podcasts or guided meditations. Her steady delivery helps listeners absorb complex information without feeling rushed.
Use Sage for tutorial segments or explanatory content. Her neutral yet engaging style ensures clarity, making technical details or step-by-step guides easy to follow.
- Clear and steady
- Educational focus
- Neutral tone
Supported Languages & Formats
Our API supports 23 languages, including French, English, German, and Spanish. Any voice can speak any supported language, ensuring consistent quality across your multilingual episodes. If you do not specify the language, the system guesses it from the script, but we recommend setting it explicitly for non-English Latin text.
23 Languages Available
We support Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Unsupported languages include Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali.
MP3, WAV, OPUS, FLAC
Choose your preferred audio format for each request. We support MP3, WAV, OPUS, FLAC, and PCM. This flexibility allows you to optimize file sizes or maintain high fidelity for archival.
Custom Speed Control
Adjust the speech rate between 0.25 and 4.0. This feature lets you speed up quick updates or slow down complex explanations, giving you precise control over the pacing of your narration.
Simple Pricing for Creators
Pricing is straightforward and scales with your usage. You pay $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. There are no monthly fees, no seats, and no minimum spend, making it easy to budget for any podcast size.
$0.01 per 1,000 Characters
Each request is charged based on the character count of your input text. Long scripts are split into parts under 4,096 characters, with each segment billed individually. This ensures you only pay for the exact narration you generate.
No Monthly Fees
We do not offer subscriptions or require a credit card on file. You can top up with USDT (TRC-20) whenever you need more capacity. Your balance never expires, so you can pause production and resume later without losing access.
Pay Only for Success
If a synthesis request fails, the charge is returned in full. You are not billed for errors, ensuring that your production costs reflect only the audio files you successfully receive and use in your shows.
Technical Integration
Integrate our TTS API into your podcast workflow using tools you already know. Our endpoint mirrors the standard OpenAI speech structure, allowing you to swap the base URL and use official OpenAI SDKs with your API key.
This compatibility means you can generate audio files instantly without building custom HTTP clients from scratch.
Simply send a POST request to https://api.playgb168.com/v1/audio/speech with your JSON payload. The API accepts standard fields like model, input, voice, and speed, returning the audio file directly in the response.
OpenAI SDK Compatible
Leverage existing OpenAI libraries by updating the base_url to https://api.playgb168.com/v1. This allows switching between providers while maintaining your current code structure.
Use any language supported by the OpenAI SDK, including Python, Node.js, and Go, to generate narration for your episodes.
- Supports official OpenAI SDKs
- Change
base_urlto use our API - Works with Python, Node.js, Go
RESTful API Endpoint
Our endpoint is POST https://api.playgb168.com/v1/audio/speech. It accepts JSON bodies and returns audio files in formats like MP3, WAV, OPUS, FLAC, or PCM.
Authentication is handled via a Bearer token in the Authorization header, ensuring secure access to your account's credits.
- Endpoint: POST /v1/audio/speech
- JSON body format
- Bearer token authentication
Easy JSON Requests
Send a simple JSON object with your text in the input field (up to 4096 characters). Specify the voice preset and optional speed between 0.25 and 4.0.
For French narration, set the language field to fr to ensure accurate pronunciation and natural storytelling flow.
- Max 4096 characters per request
- Set
languagefor French - Adjust
speedfrom 0.25 to 4.0

Quality & Licensing
Our audio quality stems from carefully curated voice presets derived from licensed recordings in the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox. This foundation ensures your podcast narration sounds natural, professional, and consistent without the need for expensive studio time or booking sessions.
Licensed Recordings
Every voice preset, from Aria’s warm narration to Felix’s energetic promo style, is built upon high-quality source material. This ensures that your generated audio maintains a polished, studio-grade character right from the first character input.
Synthetic Watermark
All generated audio files contain an inaudible watermark that clearly marks the content as synthetic speech. This transparent marking helps listeners and platforms identify AI-generated narration while maintaining the high fidelity of the audio output.
No Training Data Use
Your input text is used solely to produce the specific audio file for your request. We do not use your scripts or audio outputs to train our models, ensuring your content remains private and distinct from our training data.
Common Use Cases
Generate consistent narration for long-form content by splitting scripts into 4,096-character chunks. The API returns distinct audio files that you can seamlessly join, ensuring your audiobook maintains a professional, unified tone without expensive studio time.
Audiobook Narration
Split lengthy manuscripts into 4,096-character segments. The API returns individual audio files that you can join, maintaining consistent character voices across chapters without manual studio booking.
- Supports up to 4,096 characters per request
- Seamless audio joining for long texts
- Consistent voice across chapters
Podcast Intros
Create distinct, memorable opening sequences instantly. Use warm narrators like Aria or upbeat hosts like Nova to set the tone for your episodes, ensuring every show starts with professional clarity.
- Instant script-to-audio generation
- Distinct voice personalities
- No studio booking required
Voiceovers for Videos
Produce clear, natural-sounding commentary for visual content. Whether for tutorials or promotional clips, our 8 voice presets deliver high-quality narration that enhances viewer engagement without expensive voice talent.
- High-quality natural narration
- 8 distinct voice presets
- Ideal for tutorials and promos
Speed & Performance
Generation speed scales with text length, averaging roughly real-time performance at about 25 characters per second. Short phrases may take a few seconds to synthesize, ensuring natural pacing without excessive delay for individual segments.
Real-Time Generation
Long texts are processed efficiently, with typical output matching the duration of the spoken content. This makes it ideal for generating full episode narrations or extended audiobook chapters without significant wait times.
Queue Processing
Requests are processed sequentially, meaning under heavy load a request may wait in a queue before synthesis begins. This ensures consistent quality but may introduce slight delays during peak usage periods.
Parallel Requests
To manage processing, you can split longer scripts into parts of up to 4,096 characters and process them in parallel. Once synthesized, these audio files can be joined to create a seamless final episode.
Get Started Today
Start creating podcast content immediately with a $0.50 free trial credit, valid for 7 days when you sign in with Google. This includes approximately 50,000 characters, enough to test multiple voices and formats without any upfront commitment.
Create your account at /get-api-key/ to receive your unique API key instantly. Use it with the OpenAI SDK or standard HTTP requests to begin generating audio files right away.
Free Trial Credit
Sign up with Google to receive $0.50 in free credit, valid for 7 days. This allows you to generate about 50,000 characters of audio, perfect for testing voice quality and integration workflows.
Email/password accounts do not include this trial credit. Balance never expires, and failed requests are refunded automatically.
Instant API Key
Visit /get-api-key/ to create your account and retrieve your active API key immediately. The key starts as active upon creation, ready for use with the OpenAI SDK or direct HTTP POST requests.
Each account holds one active key. You can issue a new key at any time, which instantly deactivates the previous one.
- Supports Google Sign-In or Email/Password
- Immediate activation upon creation
- Replaceable anytime with instant deactivation
Demo Audio Samples
Experience the 8 curated voices designed for natural storytelling. From Aria’s warm narration to Felix’s energetic promo style, each voice delivers professional-grade audio for your podcast intros and voiceovers.
Test different speeds (0.25–4.0) and formats like MP3 or WAV to match your production needs. All generated files include an inaudible synthetic watermark.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice is built from licensed LibriTTS-R recordings, providing a professional foundation for high-quality audio generation.
23 languages
Any voice speaks any of these languages.
