Frequently asked questions
Is the text to voice converter free?
You receive $0.50 of free trial credit when signing in with Google, valid for 7 days. After that, usage costs $0.01 per 1,000 characters. Failed requests are free. Accounts created with email do not receive trial credit. There are no monthly plans or minimum spend requirements.
Can I use the API for corporate training?
Yes, SpeakWise is built for agencies creating corporate training content. You can send scripts via a simple API and receive clear audio files. The service handles volume so your team can focus on curriculum design. It supports multiple voices suitable for instructional and conversational training materials.
How many languages are supported?
We support 23 languages, including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any of these languages. If you do not set the language, it is guessed from the script, but you should specify it for non-English Latin-script text.
What voices are available for training?
Eight preset voices are available. For training, sage offers a calm, instructional tone, while milo provides a friendly, conversational style. Other options include aria, nova, luna, felix, atlas, and orion. All voices are based on licensed recordings and carry an inaudible synthetic watermark.
Do I need special software to use it?
No special software is required. You can use the official OpenAI SDKs by changing the base URL, or send standard HTTP requests. The API accepts JSON bodies with your text, voice selection, and format preferences. It works with any programming language that can make API calls.
Is my training data used for training?
No, your input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We keep request metadata like time and status for billing purposes, but your content remains private.
How fast is the audio generation?
Generation is roughly real time on long texts, producing about 25 characters per second of audio. Short phrases take a few seconds. Requests are processed sequentially, so under heavy load, a request may wait in a queue. Longer texts are split into 4,096-character parts.
Can I adjust the speaking speed?
Yes, you can adjust the speed between 0.25 and 4.0. This allows you to slow down complex training material or speed up simple instructions. The speed parameter is part of the standard API request body, making it easy to integrate into your automated workflows.
What formats are supported?
We support mp3, wav, opus, flac, and pcm formats. You can choose the format that best fits your learning management system or audio player. The API returns the audio file directly in the response, allowing immediate playback or storage in your corporate media library.
Is there a limit on text length?
Each API request accepts up to 4,096 characters. For longer scripts, you should split the text into parts and join the resulting audio files. Spaces and punctuation count toward the character limit. This ensures efficient processing and predictable billing for your training content projects.
Do you support SSML?
No, we do not support SSML. The API uses a simple JSON body with text input. You cannot use phoneme dictionaries or custom pronunciation lexicons. If you need specific pronunciation, you can spell words phonetically in the input text.
Can I clone my own voice?
No, we do not offer custom voice cloning. You cannot upload your own voice or design new voices. The service uses eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech.
Is there a free trial?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. There are no subscriptions, and unused balance does not expire.
How do I pay for the API?
Payments are made via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or invoices. There are no VAT invoices, monthly plans, or seats to manage for your agency.
First request
curl
curl https://api.t6slotth.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.mp3Turn Training Scripts into Audio
SpeakWise transforms your training scripts into clear audio files via a simple API. Send text, receive an audio file. You control the format, speed, and voice for each module.
Natural Voice Synthesis
Generate voiceovers for e-learning modules using eight distinct voice presets like Aria or Atlas. Each voice offers a specific tone, from warm narrators to neutral news anchors, ensuring your content sounds professional and consistent.
Easy API Integration
Integrate speech synthesis directly into your content creation workflow. Use standard JSON requests with our API, compatible with OpenAI SDKs. Manage voice selection, speed, and output format programmatically.
- Simple POST request structure
- Standard JSON input/output
- Compatible with existing SDKs
Multi-Language Support
Produce training content in multiple languages without hiring separate voice actors. Our API supports 23 languages, allowing you to scale your curriculum globally with consistent quality and tone.
Why Agencies Choose SpeakWise
Agencies scaling corporate training programs often face unpredictable volume spikes. SpeakWise handles the heavy lifting, allowing your team to focus on curriculum design rather than infrastructure management. With a simple API, you can generate thousands of audio files without worrying about server limits or bandwidth constraints, though requests are processed sequentially and may queue under load.
Cost-Effective Scaling
Our pricing model scales directly with your usage. At $10 per 1 million characters, you only pay for what you generate. Failed requests are free, ensuring you never pay for errors. This predictable cost structure helps you manage your budget effectively.
- Pay only for successful synthesis requests
- $10 per 1 million characters ($0.01 per 1,000 chars)
- No monthly plans or minimum spend requirements
No Hardware Required
SpeakWise is a cloud-based API, meaning there is no hardware to install or maintain. You send text via a simple POST request and receive an audio file. This removes the need for dedicated servers or complex deployment pipelines, letting you integrate directly into your existing workflow.
- Cloud-native architecture
- Simple HTTP POST integration
- No infrastructure maintenance required
Consistent Brand Voice
Maintaining a consistent tone across hundreds of training modules is crucial for professional branding. SpeakWise offers eight distinct voice presets, from the warm clarity of Aria to the calm instructional tone of Sage. You can select the perfect voice once and apply it consistently across all your content.
- 8 distinct voice presets
- Consistent audio quality across volumes
- Easy voice selection via API
Available Voices
SpeakWise offers eight distinct voice presets designed to match the tone of your corporate training materials. Each voice is built from licensed recordings, ensuring clarity and consistency across your curriculum.
Aria: Warm Narrator
Aria delivers a warm, clear narration style ideal for instructional content. Her tone is professional yet approachable, making complex topics easier to digest for learners.
- Best for: General training modules and onboarding videos
Nova: Upbeat Trainer
Nova brings a bright, energetic energy to your audio files. Use her voice for engaging quizzes, quick tips, or motivational segments that need to hold attention.
- Best for: Engaging quizzes and quick tip videos
Atlas: News Anchor
Atlas provides a neutral, authoritative delivery perfect for corporate updates. His clear, steady pace ensures that compliance details and policy changes are communicated with precision.
- Best for: Compliance updates and policy announcements
Supported Languages
SpeakWise supports 23 languages, allowing your training content to reach global teams without hiring local voice actors. Any voice can speak any supported language, ensuring consistent audio quality across your entire curriculum.
English and American English
English is the default for Latin-script text if no language code is set. Use the language parameter to specify variants or ensure accurate pronunciation for non-English content.
- Full support for English (default for Latin script)
- Automatic language detection for Latin script
Spanish and Latin American
Generate training modules in both Castilian and Latin American Spanish. The API handles dialect nuances automatically, ensuring clear comprehension for diverse regional teams.
- Support for Spanish (dialect nuances handled automatically)
- Clear pronunciation for corporate terminology
German and French
Expand your training library into German and French markets with native-quality synthesis. Each voice adapts to the linguistic structure, maintaining a professional tone suitable for HR and compliance videos.
- Native-level intonation and rhythm
- Support for technical vocabulary
Technical Specifications
SpeakWise delivers high-quality audio via a straightforward API. You choose between standard MP3 and uncompressed WAV formats, ensuring compatibility with any Learning Management System or playback device used in corporate training environments.
MP3 and WAV Formats
MP3 offers efficient file sizes for web delivery, while WAV provides lossless quality for archival or high-fidelity needs. Both formats are generated upon request, though processing time depends on text length and queue status.
Adjustable Speed
Control the pacing of narration between 0.25x and 4.0x. This allows trainers to create slower, clearer instructions for complex topics or faster summaries for review sessions.
Standard Encoding
The API uses standard encoding compatible with common SDKs. You can also select Opus, FLAC, or PCM formats if your specific infrastructure requires them.
- Response formats: mp3, wav, opus, flac, pcm
Pricing Model
SpeakWise charges $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you only pay for successful audio generation. This model scales effortlessly with your training volume, from short quizzes to lengthy modules.
Pay Per Character
The rate is $10 per million characters. You can process long texts by splitting them into 4,096-character chunks and joining the resulting audio files.
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free
Free Trial Credit
Sign in with Google to receive $0.50 in credit (about 50,000 characters) valid for 7 days. Email-based accounts start without trial credit.
- $0.50 credit for Google sign-ins
- Valid for 7 days
- Approximately 50,000 characters
Transparent Costs
Top-ups use USDT on the TRON network (TRC-20), minimum $5, credited within minutes. There are no monthly plans, seats, or hidden VAT fees.
- USDT (TRC-20) only
- No monthly subscriptions
- No invoices with VAT
Data Privacy
Your training scripts are processed solely to generate the requested audio files and are not used for model training. We keep only the essential request metadata—such as timestamp, character count, and status—for accurate billing and usage tracking.
Input Text Usage
Text is sent to the engine, converted to audio, and the raw input is not retained beyond the generation process. This ensures your curriculum content remains yours, with no secondary use for improving our base models.
No Training Data
Unlike many consumer services, your specific scripts are not mined to train future voice variants. The data relationship is strictly transactional: you provide text, we return audio, and nothing else is stored for machine learning purposes.
Audio Storage Policy
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. You own the resulting files and can store them in your own LMS or cloud infrastructure as needed.
Getting Started
Getting started with SpeakWise takes just a few minutes. Begin by signing up on our /get-api-key/ page using your Google account or an email and password. This creates your agency account on t6slotth.com.
Create an Account
Visit the sign-up page and choose your preferred authentication method. Google sign-in grants you an immediate $0.50 trial credit valid for 7 days, allowing you to test the API without upfront payment. Email-based accounts start without trial credit.
Generate API Key
After registration, your dashboard displays your unique API key. This key authenticates all your requests to the endpoint. You can generate a new key at any time; the previous one stops working immediately.
- Keep your key secure; it acts as your password.
First Request
Use your key to send a POST request to https://api.t6slotth.com/v1/audio/speech. Include your script in the input field and select a voice like aria or nova. The API returns an audio file ready for your training modules.
- Model:
tts-1ortts-1-hd - Format:
mp3,wav,opus,flac, orpcm
Support and Contact
SpeakWise offers straightforward assistance for agencies integrating the TTS API. Our team handles all support inquiries via email, ensuring you receive clear, actionable answers without the wait of phone trees or live chat queues. We focus on resolving technical and billing questions efficiently so your team can keep producing training content.
Email Support
Send your questions to [email protected]. We aim to respond to support inquiries via email.
Documentation
The complete API reference is available at /docs/. It includes code samples for the OpenAI SDK, endpoint details for voices and models, and clear explanations of rate limits and pricing.
- API endpoints and request formats
- Voice list and language codes
- Error codes and troubleshooting
Community
While we do not host a public forum, developers can share integration tips and workflows using the SpeakWise API. Connect with other agencies building corporate training audio through our developer channels.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.