Provider Pricing

Vowrite is free and open source. You bring your own API keys (BYOK) and only pay your chosen providers directly. Here's what they cost.

Monthly Cost Estimates

Based on ~30 minutes of voice input per day (≈15 STT hours + 300K Polish tokens / month)

🆓 Free Combo

$0/mo

SiliconFlow SenseVoice STT + Zhipu glm-4.7-flash Polish. Zero cost, unlimited usage.

💰 Budget

~$0.65/mo

Groq whisper-large-v3-turbo + DeepSeek V4-flash Polish. Excellent quality at pennies.

âš–ī¸ Balanced

~$3.30/mo

OpenAI mini-transcribe + gpt-5.4-mini. Reliable mainstream choice.

đŸŽ¯ Premium

~$9.00/mo

Deepgram Nova-3 + Claude Sonnet 4-6. Top accuracy and polish quality.

🎤 Speech-to-Text (STT)

Transcribe your voice to raw text

Provider Model Price / min Price / hour Languages
Sherpa (Offline) SenseVoice Small / Zipformer / FireRedASR2 Free 🔒 Free EN/CN/JP/KR/æ–šč¨€ 100% LOCAL
SiliconFlow FunAudioLLM/SenseVoiceSmall Free ✨ Free 50+ FREE
SiliconFlow TeleAI/TeleSpeechASR Free ✨ Free CN focused FREE
iFlytek (čŽ¯éŖž) iat / xfime-mianqie Free 500/day ~$0.002 CN + 23 dialects CN BEST
Groq whisper-large-v3 $0.0005 $0.03 57+ CHEAPEST
Groq whisper-large-v3-turbo $0.0007 $0.04 57+ FASTEST
Qwen paraformer-realtime-v2 ~$0.0014 ~$0.08 30+ VALUE
Qwen qwen3-asr-flash ~$0.0028 ~$0.17 30+ auto-detect
Together AI whisper-large-v3 $0.0015 $0.09 57+
OpenAI gpt-4o-mini-transcribe $0.003 $0.18 57+ ⭐ Default
OpenAI gpt-4o-transcribe $0.006 $0.36 57+ ACCURATE
OpenAI gpt-4o-transcribe-diarize $0.006 $0.36 57+ Speaker labels
OpenAI whisper-1 $0.006 $0.36 57+ Legacy
Deepgram Nova-3 (batch) $0.0043 $0.26 36+
Deepgram Nova-3 (streaming) $0.0077 $0.46 36+ TOP ACCURACY
Deepgram Nova-3 (multi-channel) $0.0052 $0.31 36+
Deepgram Nova-2 $0.0058 $0.35 36+ Legacy
Volcengine Seed-ASR (Doubao) Pending Pending 13+ F-063 (TOS or WS)

✨ AI Polish (LLM)

Clean up and refine your transcribed text

Provider Model Input $/M tokens Output $/M tokens Context
Ollama (Local) qwen3:8b ¡ llama3.1:8b ¡ deepseek-r1:8b ¡ gemma3:4b Free đŸ–Ĩī¸ Free Varies 100% LOCAL
MLX Server (Local) Qwen3.5-9B ¡ Llama 3.3 70B ¡ Mistral Small 24B Free đŸ–Ĩī¸ Free Varies APPLE SILICON
Zhipu glm-4.7-flash Free ✨ Free 203K FREE
Zhipu glm-4.5-air ~$0.20 ~$0.30 128K Lightweight
Zhipu glm-4.6 $0.60 $2.20 200K
Zhipu glm-5 $1.00 $3.00 200K
Zhipu glm-5.1 $0.45 $0.80 200K FLAGSHIP
Groq llama-3.1-8b-instant $0.05 $0.08 128K FASTEST
Groq openai/gpt-oss-20b $0.10 $0.50 128K
Groq openai/gpt-oss-120b $0.15 $0.60 128K ⭐ Default
Groq qwen/qwen3-32b $0.29 $0.39 128K Reasoning preview
Groq llama-3.3-70b-versatile $0.59 $0.79 128K
DeepSeek deepseek-v4-flash $0.14 $0.28 1M VALUE ⭐
DeepSeek deepseek-v4-pro $0.435 * $0.87 * 1M * 75% off till 2026-05-31
OpenAI gpt-5.4-nano $0.20 $1.25 400K CHEAPEST
OpenAI gpt-4o-mini $0.15 $0.60 128K Legacy fallback
OpenAI gpt-5.4-mini $0.75 $4.50 400K ⭐ Default
OpenAI gpt-5.5 $3.00 $15.00 400K FRONTIER
Gemini gemini-2.5-flash-lite $0.10 $0.40 1M FREE TIER
Gemini gemini-2.5-flash $0.30 $2.50 1M ⭐ Default
Gemini gemini-2.5-pro $1.25 $10.00 1M (2× >200K) FLAGSHIP
Claude claude-haiku-4-5 $1.00 $5.00 200K Fast tier
Claude claude-sonnet-4-6 $3.00 $15.00 1M PREMIUM ⭐
Claude claude-opus-4-7 $5.00 $25.00 200K Most capable
Kimi (Moonshot) kimi-k2.5 $0.60 $2.50 128K Previous flagship
Kimi (Moonshot) kimi-k2.6 $0.60 $2.50 200K ⭐ Latest
Kimi (Moonshot) kimi-k2-thinking-turbo $0.60 $2.50 200K Reasoning
MiniMax MiniMax-M2.5 $0.15 $1.15 197K
MiniMax MiniMax-M2.7-highspeed $0.30 $2.40 197K FAST
MiniMax MiniMax-M2.7 $0.30 $1.20 197K ⭐ Latest
Volcengine doubao-seed-1-6 ~$0.11 ~$1.13 256K
Volcengine doubao-seed-1-8 ~$0.11 ~$0.28 32K (cheap) ⭐ Default
Volcengine doubao-seed-2-0-pro $0.47 $2.37 256K FLAGSHIP
Qwen qwen-turbo-latest ~$0.05 ~$0.20 128K Cheap stable
Qwen qwen3.6-flash ~$0.06 ~$0.50 128K VALUE
Qwen qwen3.6-plus $0.33 $1.95 1M ⭐ Default
Qwen qwen3.6-max-preview $1.04 $6.24 1M FRONTIER
SiliconFlow Qwen/Qwen3-8B Free ✨ Free 32K FREE
SiliconFlow deepseek-ai/DeepSeek-V3 ~$0.014 ~$0.028 164K CHEAPEST
SiliconFlow deepseek-ai/DeepSeek-V3.1-Terminus ~$0.28 ~$0.42 164K
SiliconFlow zai-org/GLM-4.6 ~$0.42 ~$0.84 200K
SiliconFlow Qwen/Qwen3-235B-A22B ~$0.41 ~$0.83 128K MoE 235B
SiliconFlow Qwen/Qwen2.5-72B-Instruct ~$0.57 ~$0.57 128K
Together AI Qwen/Qwen3.5-9B $0.20 $0.20 32K Cheap & fast
Together AI meta-llama/Llama-3.3-70B-Instruct-Turbo $0.88 $0.88 128K Balanced
Together AI deepseek-ai/DeepSeek-V4-Pro ~$1.50 ~$3.00 512K Reasoning flagship
OpenRouter 300+ models (aggregator) Pass-through Pass-through Varies One key, many models
💡 How Vowrite pricing works: Vowrite itself is free and open source. You bring your own API keys (BYOK) and pay providers directly for what you use. Mix and match — use one provider for STT and another for Polish.

📌 Notes: CNY prices converted at ~ÂĨ7.2 = $1 USD (May 2026). Prices sourced from official provider pages and may change — verify on the provider's billing page before high-volume usage. Monthly estimates assume ~15 hours STT + ~300K tokens Polish per month. Models marked ⭐ are the Vowrite default for that provider.