← All models
Maya
maya-batch
Text to Speechby maya
Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
Pricing
- Price
- 0.250 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| textsrequired | array | List of texts to synthesize into speech. You can embed emotion tags in each text using the format <emotion_name>. |
| top_p | number | Nucleus sampling parameter for all generations. |
| promptsrequired | array | List of voice descriptions for each text. Must match the length of texts list. Each describes the voice/character attributes. |
| max_tokens | integer | Maximum SNAC tokens per generation. |
| sample_rate | stringenum: 48 kHz, 24 kHz | Output audio sample rate for all generations. 48 kHz provides higher quality, 24 kHz is faster. |
| temperature | number | Sampling temperature for all generations. |
| output_format | stringenum: wav, mp3 | Output audio format for all generated speech files |
| repetition_penalty | number | Repetition penalty for all generations. |
Output
| Field | Type | Description |
|---|---|---|
| audios | array | List of generated audio files |
| durations | array | Duration of each generated audio in seconds |
| average_rtf | number | Average real-time factor across all generations |
| sample_rate | string | Sample rate of all generated audio files |
| total_generation_time | number | Total time taken to generate all audio files in seconds |