Text to Speech and Transcription API
Speech synthesis and audio transcription through the OpenAI-compatible audio endpoints. One OpenAI-compatible endpoint, one API key, per-token pricing, and at least 30% below the provider's list price.
Speech synthesis and audio transcription through the OpenAI-compatible audio endpoints.
The endpoint
POST https://api.aetherapi.dev/v1/audio/speechWhat this gives you
- Speech synthesis and transcription, both on the standard audio endpoints
- Several voices and languages, priced per 1M characters or per minute of audio
- The same key as the models that write the text you want to hear
Models for this endpoint
| Model | Context | Price |
|---|---|---|
| GPT 4o Mini TTS | — | $8.4/M input | $8.4/M output |
| TTS 1 | — | $10.5/M input | $10.5/M output |
| TTS 1 HD | — | $21/M input | $21/M output |
| GPT 4o Mini Transcribe | — | $0.0021/M input | $0.0021/M output |
| GPT 4o Transcribe | — | $0.0042/M input | $0.0042/M output |
| Whisper 1 | — | $0.0042/M input | $0.0042/M output |
Related
See every model on the models page, the credit packages, and the quickstart. Other kinds of work: Chat API · Image Generation API · Embeddings API · Video Generation API
Aether API — OpenAI-compatible access to 13+ providers through one API key.