Whisper Large v3 Turbo

Speech to text · Multilingual transcription

$0.0003 per minute of audio

For Chinese and English transcription, choose qwen3-asr: 0.3–0.7 s on 3–8 s clips, measured 2026-10-12. Choose whisper-large-v3-turbo for Whisper parity; whisper-1 is its compatibility alias.

OpenAI list prices: whisper-1 $0.006 per minute; tts-1 $15 per 1M characters.

measured 2026-10-12: 0.4–3.3 s (3–8 s audio)

Upload limit: 25 MB for the multipart request; four parts maximum, one non-empty audio file, and 8 KB of headers per part. The body must arrive within 120 seconds and average at least 16 KB/s over every 10-second window after the first 10 seconds. Each key can have two simultaneous uploads; shared spool limits return 429 with Retry-After.

Formats: json (default), text, verbose_json, srt, vtt. Duration billing is identical for every response format.

voice is optional. Chatterbox Turbo passes any voice string through. Qwen3 TTS ignores voice.

Transcription supports file, model, language, prompt, temperature and timestamp_granularities[] (word, segment). Speech supports model, input, optional voice, response_format and speed (0.25–4).

Transcription reserves upload bytes ÷ 250 (2 kbit/s), capped at 24 hours; valid WAV/PCM headers provide the exact duration instead. Settlement always uses the real duration reported by the model, even above the estimate. Speech reserves the exact input character count and charges in full when the provider completes, or when the client disconnects or stalls after receiving at least one audio byte. Provider failures and timeouts are not billed, including partial delivery. No minimum charge.

Compatibility aliases: whisper-1 → whisper-large-v3-turbo; tts-1 → qwen3-tts. tts-1 is billed as qwen3-tts ($25 per 1M characters). chatterbox-turbo is $1.50 per 1M characters, English only; select it explicitly. Billing and reporting use canonical IDs.

curl https://api.quicksilverpro.io/v1/audio/transcriptions \
  -H "Authorization: Bearer $QSP_KEY" \
  -F "model=whisper-large-v3-turbo" \
  -F "[email protected];type=audio/wav" \
  -F "response_format=json"