Documentation
Everything you need to integrate Sayd into your application.
Talk API
Push-to-talk voice input with AI-powered transcript cleaning. WebSocket streaming + LLM processing.
Listen API
Real-time speech-to-text via WebSocket. Raw transcription without AI cleaning β you control the pipeline.
Transcribe API
Upload audio files for async transcription. Supports WAV, MP3, and more. Results via polling.
VAD API
Voice Activity Detection β detect speech segments or check if audio contains speech.
Getting Started
The fastest way to get started:
- Create a free account and get your API key
- Follow the Quick Start guide
- Explore the Talk API documentation
Supported Languages
Sayd supports real-time transcription and translation in 60+ languages. All languages work with both the Real-time Streaming API and the Batch Transcription API. Mixed-language speech (code-switching) is automatically detected.
| Language | ISO Code | Language | ISO Code |
|---|---|---|---|
| Afrikaans | af | Albanian | sq |
| Arabic | ar | Azerbaijani | az |
| Basque | eu | Belarusian | be |
| Bengali | bn | Bosnian | bs |
| Bulgarian | bg | Catalan | ca |
| Chinese | zh | Croatian | hr |
| Czech | cs | Danish | da |
| Dutch | nl | English | en |
| Estonian | et | Finnish | fi |
| French | fr | Galician | gl |
| German | de | Greek | el |
| Gujarati | gu | Hebrew | he |
| Hindi | hi | Hungarian | hu |
| Indonesian | id | Italian | it |
| Japanese | ja | Kannada | kn |
| Kazakh | kk | Korean | ko |
| Latvian | lv | Lithuanian | lt |
| Macedonian | mk | Malay | ms |
| Malayalam | ml | Marathi | mr |
| Norwegian | no | Persian | fa |
| Polish | pl | Portuguese | pt |
| Punjabi | pa | Romanian | ro |
| Russian | ru | Serbian | sr |
| Slovak | sk | Slovenian | sl |
| Spanish | es | Swahili | sw |
| Swedish | sv | Tagalog | tl |
| Tamil | ta | Telugu | te |
| Thai | th | Turkish | tr |
| Ukrainian | uk | Urdu | ur |
| Vietnamese | vi | Welsh | cy |
π‘ Auto Language Detection You don't need to specify the language β Sayd automatically detects the spoken language and handles mid-sentence language switching. Translation works between any pair of the 60+ supported languages (3,600+ combinations).
Why Sayd?
| Feature | Sayd | Traditional APIs |
|---|---|---|
| Latency | < 200ms first byte | 500ms+ |
| Pricing | Token-based, from $0 | Per-minute, minimums |
| Agent Integration | Native support | Manual wiring |