Complete speech generation and transcription

Handle binary speech, asynchronous speech tasks, and multipart transcription correctly.

Choose an audio model in the marketplace

Speech synthesis workflow

Submit exactly one of input or prompt, plus any model-specific fields. Save audio/* responses directly; for application/json, read the task ID and poll it.

curl

Python

Node.js

#!/usr/bin/env bash
set -euo pipefail

headers=$(mktemp)
body=$(mktemp)
trap 'rm -f "$headers" "$body"' EXIT

curl -fsS -D "$headers" -o "$body" https://api.noxgate.net/v1/audio/speech \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","input":"Hello from NoxGate","voice":"YOUR_VOICE_ID"}'

content_type=$(awk -F': *' 'tolower($1) == "content-type" {print tolower($2)}' "$headers" | tail -1 | tr -d '\r')
if [[ "$content_type" != application/json* ]]; then
  mv "$body" speech.mp3
  echo "Saved speech.mp3"
  exit 0
fi

response=$(cat "$body")
task_id=$(printf '%s' "$response" | jq -r '.id // empty')
status=$(printf '%s' "$response" | jq -r '.status // empty')
deadline=$((SECONDS + 300))
delay=2
while [[ -n "$task_id" && "$status" != "succeeded" ]]; do
  case "$status" in failed|canceled|cancelled) printf '%s\n' "$response" >&2; exit 1 ;; esac
  [[ $SECONDS -ge $deadline ]] && { echo "Speech generation timed out" >&2; exit 1; }
  sleep "$delay"
  response=$(curl -fsS "https://api.noxgate.net/v1/audio/speech/$task_id" \
    -H "Authorization: Bearer sk-your-api-key")
  status=$(printf '%s' "$response" | jq -r '.status // empty')
  (( delay < 10 )) && delay=$((delay + 2))
done

result_url=$(printf '%s' "$response" | jq -r '.url // empty')
[[ -n "$result_url" ]] || { printf '%s\n' "$response" >&2; exit 1; }
if [[ "$result_url" == /* ]]; then result_url="https://api.noxgate.net$result_url"; fi
curl -fL "$result_url" -o speech.mp3
echo "Saved speech.mp3"

Audio transcription workflow

Transcription requires a real multipart/form-data upload; a local path inside JSON is not a file upload.

curl

Python

Node.js

curl https://api.noxgate.net/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "model=YOUR_MODEL_ID" \
  -F "file=@./audio.mp3"

Results and errors

Voice, format, file type, and optional parameters depend on the model.
Async clients must handle failed, canceled, and cancelled, with a total timeout.
Download an async result URL promptly; do not assume it remains valid forever.