Paxa Labs

Inspect and control the shared audio queue. status reports what is playing, what is queued, and any synthesis failures. pause and resume halt and continue playback (not supported on Windows). skip drops the current segment. clear stops playback and empties the queue.

Extract typed fields from a local PDF, PNG, JPEG, or WebP document (up to 20 pages and 10 MiB) with Paxa Document Extraction. You write a schema of fields; every value returned is text printed in the document, read as the field's type, or null with the reason. Nothing is inferred or looked up. Built for Thai documents (receipts, tax invoices, forms, IDs) and fine on English ones. Costs 13 credits per page for a schema of up to 50 leaf fields and 19.5 per page for 51 to 100; the page reading and the evidence spans cost nothing extra. A schema the API refuses costs nothing and names the field and reason. The schema parameter summarizes the dialect; https://paxalabs.com/docs/extraction has every type and key.

Show the API key's account: credit balance, plan, and rate limits. Free.

List available Paxa models with their limits and credit pricing. Free.

List the Paxa TTS voice roster: ids, names, gender, language, and character notes. Free.

Record one spoken turn from this machine's microphone and return its transcript (Thai, English, or other languages, code-switching included). Paxa's realtime transcription detects when the user starts and stops talking, so the call returns as soon as the turn ends; the audio goes straight to the API and nothing is written to disk. Waits for any speech this server is playing to finish first. Use it after speak when you asked the user a question and want their spoken answer. Returns an empty transcript when nobody spoke within wait_seconds. Costs 12.5 credits per minute of audio sent, silence included (a few seconds of listening costs well under one credit). Needs a microphone recorder on this machine (ffmpeg or sox; parecord or arecord on Linux) and Node 22 or newer; the host app must have microphone permission.

Run Paxa OCR on a local PDF, PNG, JPEG, or WebP file and return its content as GitHub-flavored Markdown (or structured blocks). Up to 50 pages and 10 MiB per file. Costs 6.5 credits per page.

Play a local audio file through this machine's speakers, for example a file produced earlier by text_to_speech. Blocks until playback finishes. Free (no API call).

Read long content aloud (stories, articles, books). Splits the text into segments, synthesizes ahead while playing, and returns immediately; segments play in order after anything already queued. Monitor and control with the control_playback tool. Costs 10 credits per 1000 characters. On the experimental voices khanomchan and kaprao, a bracketed emotion tag written into the text, such as [happy] or [sad:0.6], changes the delivery from that point on. Every other voice skips the tags.

Report a wrong or poor output, an API problem, or a platform issue to the Paxa Labs team, tied to the request ids the other tools print ("Request id: ..."). A rating alone on at least one request id is a complete report. For a wrong output, add an example with the exact input, the output received, and the output expected. Free, no credits. Use it when the user says an output was wrong, or asks to report a problem; do not file reports the user did not ask for.

Synthesize a short line with Paxa TTS and play it through this machine's speakers. Blocks until playback finishes. Waits for the currently playing audio but jumps ahead of queued long-form segments. For long content use queue_speech. Costs 10 credits per 1000 characters. On the experimental voices khanomchan and kaprao, a bracketed emotion tag written into the text, such as [happy] or [sad:0.6], changes the delivery from that point on. Every other voice skips the tags.

Synthesize speech with Paxa TTS and save it as an audio file without playing it: voiceovers, narration, audiobooks. Text beyond 5000 characters is split at paragraphs and sentences and the parts are joined into one file (needs ffmpeg). With subtitles set, an srt or vtt caption file that matches the voice word for word is written next to the audio. Costs 10 credits per 1000 characters, 12.5 with subtitles. On the experimental voices khanomchan and kaprao, a bracketed emotion tag written into the text, such as [happy] or [sad:0.6], changes the delivery from that point on. Every other voice skips the tags.

Transcribe a local recording or video of speech, Thai or any other language, code-switching included (mp3, wav, flac, ogg, m4a, aac, webm; or mp4, mov, mkv, avi and other video files, whose sound track is extracted locally with ffmpeg; up to 60 minutes and 25 MiB) with Paxa STT. The transcript comes back inline, so nothing needs to be read from disk afterwards; optionally it is also saved as txt, json (with word timings and segments), srt, or vtt, named after the recording. Existing files are never overwritten. Detects the language, handles code-switching, and can label speakers. Terms configured in PAXA_VOCABULARY or PAXA_VOCABULARY_FILE are pinned on every call. Costs 8.33 credits per minute of audio (0.1 minimum); subtitles and word timings cost nothing extra. Long recordings take minutes to process.

Translate text from any language into Thai with Paxa Translate. Accepts a single string or up to 200 segments that share context. Costs 25 credits per 1000 text characters (minimum 2 credits); context and glossary characters bill at 8 per 1000.