Prices in USD · per minute
| Compare | Speech-to-Text, Text-to-Speech, or Realtime | Cost per minute of audio input | Cost per minute of audio output | |
|---|---|---|---|---|
| OpenAI | ||||
| Whisper | Speech-to-Text | $0.0060 | — | |
| TTS | Text-to-Speech | — | $0.015 | |
| TTS HD | Text-to-Speech | — | $0.03 | |
| GPT-4o Audio | Realtime | $0.60 | $2.40 | |
| Groq | ||||
| Whisper Large v3 Turbo | Speech-to-Text | $0.000670 | — | |
| Whisper Large v3 | Speech-to-Text | $0.0019 | — | |
| Orpheus TTS (English) | Text-to-Speech | — | $22.00per 1M chars | |
| Orpheus TTS (Arabic) | Text-to-Speech | — | $40.00per 1M chars | |
| Stability AI | ||||
| Stable Audio 2.5 | Text-to-Audio | — | $0.20per generation | |
| Stable Audio 3.0 | Text-to-Audio | — | $0.26per generation | |
| Gemini 2.5 Flash TTS | Text-to-Speech | $0.50per 1M tokens | $10.00per 1M tokens | |
| Gemini 2.5 Pro TTS | Text-to-Speech | $1.00per 1M tokens | $20.00per 1M tokens | |
| Gemini 3.1 Flash TTS | Text-to-Speech | $1.00per 1M tokens | $20.00per 1M tokens | |
| Gemini 2.5 Flash Native Audio | Realtime | $3.00per 1M tokens | $12.00per 1M tokens | |
| Gemini 3.1 Flash Live | Realtime | $3.00per 1M tokens | $12.00per 1M tokens | |
| Gemini 3.5 Live Translate | Realtime | $3.50per 1M tokens | $21.00per 1M tokens | |
| Azure AI | ||||
| Whisper | Speech-to-Text | $0.0060 | — | |
| TTS | Text-to-Speech | — | $0.015 | |
| TTS HD | Text-to-Speech | — | $0.03 | |
| GPT-4o Audio | Realtime | $0.60 | $2.40 | |
| GPT-4o Transcribe | Speech-to-Text | $6.00per 1M tokens | $10.00per 1M tokens | |
| GPT-4o mini Transcribe | Speech-to-Text | $3.00per 1M tokens | $5.00per 1M tokens | |
| GPT-4o mini TTS | Text-to-Speech | $0.60per 1M tokens | $12.00per 1M tokens | |
| AWS Bedrock | ||||
| Amazon Nova Sonic | Realtime | $3.40per 1M tokens | $13.60per 1M tokens | |
| Together AI | ||||
| Orpheus 3B | Text-to-Speech | — | $15.00per 1M chars | |
| Cartesia Sonic | Text-to-Speech | — | $65.00per 1M chars | |
| Cartesia Sonic 2 | Text-to-Speech | — | $65.00per 1M chars | |
| Cartesia Sonic 3 | Text-to-Speech | — | $65.00per 1M chars | |
| Kokoro 82M | Text-to-Speech | — | $10.00per 1M chars | |
| Nemotron 3 ASR Streaming 0.6B | Speech-to-Text | $0.0015 | — | |
| Nemotron 3.5 ASR Streaming 0.6B | Speech-to-Text | $0.0045 | — | |
| Parakeet TDT 0.6B v3 | Speech-to-Text | $0.0015 | — | |
| Whisper Large v3 | Speech-to-Text | $0.0015 | — | |
| Z.ai | ||||
| GLM-ASR | Speech-to-Text | $0.03per 1M tokens | — | |