Cloud Text-to-Speech API for Transit Announcements

By ClearCast editorial team · Updated 2026-11-18

ClearCast provides a cloud Text-to-Speech API designed to help transport product teams generate crisp, natural-sounding audio for station announcements, app notifications, and digital signage. We simplify the process of creating clear updates for bus and train delays or platform safety warnings, ensuring your passengers receive accurate information without technical friction.

This page outlines how our API integrates into your workflow, offering a free MP3 download tool and scalable pricing. Whether you are building in-app notifications or automating digital signage scripts, you will find the specific tools, voice options, and technical details needed to deploy high-quality audio efficiently.

Cloud Text-to-Speech API for Transit Announcements

Frequently asked questions

Is the text to speech online really free?

Yes, you can download MP3 files for free without creating an account. If you need the API for automation, a free trial provides $0.50 credit (about 50,000 characters) valid for 7 days when signing in with Google. Standard pricing is $10 per million characters.

Can I download unlimited MP3 files?

Yes, you can download MP3 files directly from the website without any account required. This is ideal for testing voices or generating simple announcements. For higher volume usage via the API, you pay $0.01 per 1,000 characters, with no monthly plans or minimum spend.

Which voices work best for announcements?

For station announcements, we recommend atlas (neutral, news) or milo (friendly, conversational). Sage offers a calm, instructional tone suitable for instructions, while aria provides a warm, clear narrator style. All eight voices support all 23 languages, allowing you to choose the best fit for your transit context.

Do I need to create an account to download?

No, you can download MP3 files directly without creating an account. If you want to use the API to generate audio programmatically, you must create an account on the /get-api-key/ page. You can sign up with Google or an email and password to receive your API key.

What languages are supported for transit?

We support 23 languages including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and Portuguese. Any voice can speak any of these languages. If you do not set the language parameter, it is guessed from the script, but we recommend setting it explicitly for non-English Latin-script text.

Can I use the audio for commercial purposes?

Yes, the audio is generated from licensed recordings and public-domain audiobook readings. The generated files carry an inaudible watermark marking them as synthetic speech. You can use the audio for commercial purposes such as station announcements, app notifications, and digital signage without additional licensing fees beyond your API usage.

Is there a limit on text length per request?

Yes, each API request accepts up to 4,096 characters in the input field. For longer texts, you should split them into parts of up to 4,096 characters and join the resulting audio files. Spaces and punctuation count toward the character limit and pricing.

Do you support SSML for emphasis?

No, we do not support SSML (Speech Synthesis Markup Language). The API accepts plain text input. If you need emphasis or pacing, you can adjust the overall speed between 0.25 and 4.0, or choose a voice preset that naturally fits your desired tone and delivery style.

Can I clone my own voice for announcements?

No, we do not offer custom voice cloning or uploading your own voice. We provide eight preset voices based on licensed recordings. If you need a specific tone, you can choose from options like atlas for news or milo for a friendly, conversational style.

How fast is the generation process?

Generation is roughly real-time on long texts, processing about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under heavy load, a request might wait in a queue. The typical speed is sufficient for most transit announcement workflows.

Is the API compatible with other tools?

Yes, the API endpoint matches the OpenAI speech endpoint shape. You can use the official OpenAI SDKs by changing the base_url to https://api.playc54.com/v1. It also works with any HTTP client that can send JSON POST requests with the required fields like model, input, and voice.

What happens if the generation fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or check your balance and usage on the dashboard. Failed requests do not consume your character allowance or affect your billing for that specific attempt.

Can I change the speed of the audio?

Yes, you can adjust the speed between 0.25 and 4.0 using the speed parameter in your API request. This allows you to make announcements faster for quick updates or slower for clarity. The default speed is 1.0, providing a natural pace for most transit contexts.

Is my text data stored after download?

No, your 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. We keep request metadata like time, characters, and status for billing purposes, but the actual text content is not retained.

First request

curl

curl https://api.playc54.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

Instant Audio for Transit Announcements

Sound wave illustration for: Instant Audio for Transit Announcements

Generate crisp transit announcements instantly with ClearCast. Our cloud API delivers natural-sounding audio for station updates, delay notifications, and safety warnings, helping product teams keep passengers informed without manual recording.

Upload your script, pick a voice, and receive an MP3 file. It’s that simple to maintain clear communication across your network.

Clear station updates

Clear station updates

Deliver precise platform instructions and service changes. Our voices ensure every word is understood, reducing confusion during peak hours.

  • Natural narration for platform info
  • Instant MP3 delivery

Bus and train delays

Communicate real-time schedule adjustments quickly. Whether it’s a minor delay or a major disruption, get audio ready in seconds.

  • Real-time delay scripts
  • Consistent tone across updates

Platform safety warnings

Issue clear, calm safety alerts. Use neutral or instructional voices to ensure passengers notice critical information without causing alarm.

  • Calm safety alerts
  • Clear instruction tones

Why Product Teams Choose Us

Sound wave illustration for: Why Product Teams Choose Us

Product teams need reliable audio without hunting for hidden constraints. ClearCast lets you download MP3s for free via our web tool, making it easy to prototype station announcements or app notifications. You can generate as much audio as you need during the trial or your own projects, ensuring your workflow isn't bottlenecked by arbitrary download caps.

Unlike platforms that charge per voice or lock you into complex subscriptions, we offer eight distinct presets for various tones. Whether you need a calm instructional voice for safety warnings or a friendly conversational tone for delays, you get immediate access without extra fees. This simplicity means your team can focus on content, not configuration.

No character limits on downloads

Download unlimited MP3s for free. Perfect for testing station scripts or building a library of loopable audio assets.

Multiple voice options

Eight voices range from warm narrators to energetic promo styles. All voices support 23 languages, allowing you to maintain brand consistency across global networks.

  • 8 distinct voice presets
  • Support for 23 languages
  • Consistent quality across voices

Simple MP3 format

Get standard MP3 files ready for immediate integration. No complex processing or proprietary formats required for your digital signage or app players.

  • Standard MP3 output
  • Ready for immediate playback
  • Compatible with all players

Voices for Every Tone

Sound wave illustration for: Voices for Every Tone

ClearCast offers eight distinct voice presets designed to match the specific mood of your transit communications. Each voice is derived from licensed recordings, ensuring a natural, human-like quality.

Calm instructional voice

Sage provides a steady, clear tone ideal for safety instructions or platform guidance. Its neutral delivery ensures passengers absorb critical information without distraction, making it perfect for repeated loop announcements.

  • Sage: Calm, instructional

Friendly conversational tone

Milo offers a warm, approachable sound suitable for app notifications or welcome messages. The conversational style makes digital signage feel more personal, helping to soften the experience of waiting for delayed services.

  • Milo: Friendly, conversational

Neutral news style

Atlas delivers a standard, professional voice similar to traditional broadcast news. It is reliable for delivering delay updates or schedule changes where clarity and neutrality are prioritized over emotional expression.

  • Atlas: Neutral, news

Languages for Global Networks

Sound wave illustration for: Languages for Global Networks

ClearCast supports 23 languages, allowing you to broadcast consistent, high-quality announcements across diverse passenger bases. Each voice can speak any supported language, ensuring natural delivery regardless of the speaker’s native tongue.

Whether you need simple Latin-script text or specific regional dialects, our API handles the nuances automatically. Set the language parameter explicitly for non-English texts to avoid guessing errors.

English and Spanish

English and Spanish are fully supported with dedicated voice presets optimized for clarity in transit environments. These languages cover the majority of global transport networks, from local bus routes to international rail systems.

Our voices handle mixed-language scripts naturally, making them ideal for bilingual stations or routes serving diverse communities.

  • Dedicated presets for English and Spanish
  • Natural handling of mixed scripts
  • Optimized for transit clarity

French and German

French and German speakers receive crisp, articulate audio suitable for both announcements and informational updates. The voices maintain a neutral, professional tone that works well for safety warnings and schedule changes.

No additional configuration is needed; simply select the voice and input your text in the target language.

  • Crisp articulation for safety warnings
  • Professional tone for schedule updates
  • Zero configuration required

Asian and European languages

We support 23 languages in total, including Japanese, Korean, Chinese, Arabic, Hindi, and several others. This broad coverage ensures you can serve global networks without managing multiple vendors.

Each language is powered by the same high-quality engine, ensuring consistent audio quality across all supported regions.

  • 23 total languages supported
  • Includes Asian and European options
  • Consistent quality across regions

How It Works

Sound wave illustration for: How It Works

Generate transit audio in three simple steps. Our workflow is designed for speed and ease, letting you focus on your content rather than technical details.

Enter your text

Type or paste your announcement script into the input field. You can handle up to 4,096 characters per request, covering everything from brief delay notices to detailed platform instructions.

Select your voice

Choose from eight distinct voice presets, such as the calm instructional tone of Sage or the friendly conversational style of Milo. Our system automatically detects the language for Latin scripts, defaulting to English unless specified.

Download MP3

Receive your generated audio file instantly. You can download the MP3 directly for immediate use in digital signage or apps, or scale up using our API for automated workflows.

  • Supports MP3, WAV, OPUS, FLAC, and PCM formats
  • Adjustable speed from 0.25x to 4.0x
  • No character limits for direct downloads
How It Works

API for Automation

Sound wave illustration for: API for Automation

Integrate ClearCast directly into your transit management systems. Our endpoint mirrors the OpenAI speech API, allowing you to swap the base URL and use existing OpenAI SDKs without rewriting your code. This compatibility simplifies deployment for teams already familiar with standard TTS workflows.

Generate audio files programmatically for automated station announcements or app notifications. The API processes requests sequentially, ensuring consistent quality while scaling with your network's needs.

OpenAI compatible SDK

Use the official OpenAI SDKs by simply pointing them to our base URL (https://api.playc54.com/v1). Pass your API key via the Authorization header, and all standard parameters like model, voice, and input work exactly as documented.

This approach lets you leverage existing client libraries in Python, JavaScript, and Go, reducing integration time for your engineering team.

  • Compatible with OpenAI Python/Node/Go SDKs
  • Standard POST /v1/audio/speech endpoint
  • Drop-in replacement for existing TTS integrations

Real-time generation

While not streaming, the API returns complete audio files quickly. Short phrases generate in seconds, and longer texts process at roughly real-time speed (25 characters per second). Requests are queued sequentially to maintain stability under load.

This predictable latency works well for pre-scheduled announcements or triggered in-app notifications where immediate millisecond precision isn't critical.

  • Generates complete MP3/WAV/OPUS/FLAC/PCM files
  • Processing speed matches real-time for long texts
  • Sequential processing ensures queue stability

Scalable pricing

Pay only for what you generate: $10 per million characters ($0.01 per 1,000 characters). Failed requests are free, so you only pay for successful audio generation. There are no monthly plans, seats, or minimum spends.

Top up via USDT (TRC-20) for instant credit. Your balance never expires, making it easy to scale usage for large transit networks without complex billing cycles.

  • $0.01 per 1,000 characters
  • No monthly plans or seats
  • Pay only for successful requests

Use Cases in Transport

Sound wave illustration for: Use Cases in Transport

Integrate ClearCast into your transit ecosystem to deliver consistent, high-quality audio across all touchpoints. Whether it’s a digital screen at a busy station or a push notification in your mobile app, our API ensures your messages are clear and natural.

By automating audio generation, product teams can update announcements instantly without recording studios. This reduces production time and keeps your communication aligned with real-time events like delays or gate changes.

Digital signage scripts

Generate crisp MP3 files for platform safety warnings and delay updates. Since the API handles up to 4096 characters per request, you can script entire announcements in one call.

  • Real-time delay announcements
  • Platform safety warnings
  • Station identification cues

In-app notifications

Provide audio cues for bus and train schedules directly in your mobile app. Use the OpenAI-compatible SDK to trigger speech generation based on user location or ride status.

  • Arrival notifications
  • Gate change alerts
  • Accessibility audio prompts

Customer service bots

Enhance chatbots with natural-sounding responses for common transit queries. Switch voices like Milo for conversational tones or Atlas for neutral updates to match the context of the query.

  • Automated ticket info
  • Route guidance
  • Multilingual support

Technical Specs

Sound wave illustration for: Technical Specs

ClearCast provides a straightforward API for generating high-quality audio files tailored to transit environments. You control the output format and playback speed to match your specific digital signage or app requirements.

MP3 and WAV formats

Choose between MP3 for efficient storage and WAV for uncompressed playback. Both formats are delivered directly via the API response.

Speed control

Adjust speech speed from 0.25x to 4.0x. This allows you to fine-tune announcements for busy stations or quiet platforms without re-recording.

Character limits

Each API request accepts up to 4,096 characters. For longer announcements, split the text into parts and join the resulting audio files.

Get Started Today

Sound wave illustration for: Get Started Today

Start generating transit announcements immediately with a free $0.50 trial credit. This balance covers approximately 50,000 characters, allowing your product team to test voice quality and integration without any financial commitment.

Create your account using Google or an email address. You receive immediate access to the API dashboard, where you can view your key, usage metrics, and ready-to-use curl examples.

Free trial credit

Receive $0.50 in credit upon signing in with Google. This amount is sufficient to generate roughly 50,000 characters of audio, enough to test multiple station scripts or bus delay notifications.

No credit card needed

Begin your trial without entering payment details. You can explore the API capabilities and download MP3 files directly from the dashboard before deciding to top up via USDT (TRC-20).

Accounts created with email and password do not include the trial credit, but still provide full access to the API and documentation.

Instant access

Your API key is generated immediately after sign-up. You can start sending POST requests to the speech endpoint or use the OpenAI SDK by adjusting the base URL.

Top-ups are processed automatically within minutes after a TRON network transfer, ensuring your service remains uninterrupted as you scale from testing to production.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Aria delivers a soft, storytelling quality that works well for detailed route explanations or station history segments.

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. IETF RFC 7845: Ogg Opus
  3. Creative Commons Attribution 4.0
  4. openai-node on GitHub
  5. TRON developer hub: TRC-20
  6. LibriTTS-R corpus (OpenSLR 141)
  7. curl documentation
  8. LibriTTS-R paper (arXiv 2305.18802)
  9. Tether (USDT)
  10. OpenAI API reference: create speech
  11. MDN: Web Speech API
  12. ISO 639 language codes

More on this site