Paxa Labs API
API by Paxa Labs · rest
Text to speech for Thai, English, and Mandarin Chinese, multilingual transcription, multilingual document OCR, and translation between 15 languages. Document Extraction pulls typed fields from documents against a schema you write. Authenticate with an API key from the dashboard. Send it as 'Authorization: Bearer pxa_...' or in the x-api-key header. Authorization wins when both are present. Costs are charged in credits and refunded automatically when inference fails. Every error is an RFC 9457 problem+json body whose title field is a stable machine-readable code. Report a wrong output or an API problem to POST /v1/feedback with the request's x-request-id. OpenAPI does not describe WebSockets (/v1/tts/live, /v1/tts/multi, /v1/stt/live, /v1/stt/multi); the docs at https://paxalabs.com/docs do.
Endpoint: https://api.paxalabs.com/
Verification: observed. Source: crawl.
Capabilities (21)
- Health check
- List speech models for OpenAI-compatible apps
- Synthesize speech (OpenAI-compatible)
- Transcribe a recording (OpenAI-compatible)
- List voices for OpenAI-compatible apps
- Extract fields from a document
- List feedback
- Send feedback
- Get key balance and plan
- List models
- Read a document
- Transcribe a recording
- Translate text
- Synthesize speech
- Synthesize a dialogue
- List voices
- Design a voice
- List designed voices
- Save a designed voice
- Rename a designed voice
- Delete a designed voice