Text to Speech - Customizable TTS
Example of voice customization (mixing): "am_adam(3)+am_eric(1)" The above example would result in an voice that is 75% am_adam and 25% am_eric. You may also use decimals to mix: "am_adam(0.6)+am_eric(0.4)" Available voices and their voice codes: | Voice Type | Voice Code | | :--- | :--- | | American Female | af_alloy | | American Female | af_aoede | | American Female | af_bella | | American…
6 subscribers
8.6/10 popularity
14264 ms avg latency
100% success rate
6 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Text to Speech - Customizable TTS endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Create Speech /v1/audio/speech |
OpenAI-compatible endpoint for text-to-speech |
| POST |
Create Timestamped Speech /dev/captioned_speech |
Generate audio with word-level timestamps. Example request: `{ "input": "Hello, This is a test.", "voice": "am_adam", "response_format": "mp3", "speed": 1, "return_timestamps":… |
| GET |
Download Audio File /v1/download/{filename} |
Download a generated audio file from temp storage. |
| POST |
Phonemize Text /dev/phonemize |
Convert text to phonemes. Args: request: Request containing text and language Returns: Phonemes and token IDs |
| POST |
Create Speech from Phonemes /dev/generate_from_phonemes |
Generate audio directly from phonemes. |
| GET |
Download Timestamps JSON file /dev/timestamps/{filename} |
Download the timestamps JSON file from temp storage. |
Text to Speech - Customizable TTS pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $1 / month | — |
|
| ULTRA Recommended | $5 / month | — |
|
| MEGA | $15 / month | — |
|
