# Cloud Speech-to-Text API
> Convert speech audio to text with Google Speech-to-Text. Supports 125+ languages, short and long audio, streaming-style workflows, speaker diarization, word timestamps, phrase hints, custom classes, profanity filtering, and punctuation.

## Agent Summary
- FQN: `solana-foundation/google/speech`
- Category: ai_ml
- Operator: solana-foundation
- Origin: google
- Version: v1
- Endpoints: 1
- Pricing: $0.02
- HTML page: https://pay.sh/services/solana-foundation/google/speech
- Markdown page: https://pay.sh/services/solana-foundation/google/speech/index.md

## Service URLs
- Gateway: https://speech.google.gateway-402.com
- Source: solana-foundation/pay-skills
- Source path: providers/solana-foundation/google/speech/PAY.md
- Source skill: pay-skills

## Use Case
Use for audio transcription, meeting notes, podcast and video captions, call center analytics, voice command processing, accessibility, diarized conversations, timestamped transcripts, domain vocabulary hints, and long audio jobs.

## Endpoint Table
| Method | Path | Pricing | Description |
| --- | --- | --- | --- |
| POST | v1/speech:recognize | $0.02/requests | Performs synchronous speech recognition: receive results after all audio has been sent and processed. |