Elevenlabs Flash V2.5
Playground
Try it on WavespeedAI!ElevenLabs Flash v2.5 is a text-to-speech model on WaveSpeedAI, billed at $0.05 per 1000 characters for generated speech. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
ElevenLabs — Flash v2.5 Text-to-Speech
ElevenLabs Flash V2.5 text-to-speech model Generates natural-sounding speech from written text. Delivers clear pronunciation, smooth pacing, and expressive tone—ideal for voiceovers, narration, and digital content. We offer a rich, built-in library of multi-lingual voices.
🎧 Key Features
- Fast generation with consistent, humanlike intonation and timing
- Multilingual capability with strong English number/date reading
- Fine control of timbre and delivery via similarity and stability
- Speaker Boost for crisper English numerals, times, and measurements
- Large built-in voice library; supports your custom voice IDs. See voice list here
💰 Pricing
- $0.05 per 1,000 characters
- If the input length is less than 1000 characters, it will be counted as 1000 characters to pay.
🚀 How to Use
- Enter your script in the text field.
- Set voice_id to a built-in or custom voice (for example: Gigi, Callum, Alice). See the full catalog in the voice list above.
- Tune delivery with the optional controls • similarity: 0–1 (higher = closer to the base voice’s timbre) • stability: 0–1 (higher = more consistent delivery) • use_speaker_boost: improves English number and unit reading
- Click Run to synthesize and preview your audio.
📝 Notes
- Output format on the platform is MP3.
- Split very long text into smaller paragraphs for more stable prosody.
- Punctuation guides rhythm—prefer clear sentences over run-ons.
- voice_id must be valid; if you see a voice error, pick one from the official voice list.
- For financial, time, or measurement content, keep use_speaker_boost enabled for best readability.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/elevenlabs/flash-v2.5" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"voice_id": "Alice",
"similarity": 1,
"stability": 0.5,
"use_speaker_boost": true
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| text | string | Yes | - | - | Text to convert to speech. Every character is 1 token. Maximum 10000 characters. Use <#x#> between words to control pause duration (0.01-99.99s). |
| voice_id | string | Yes | Alice | Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill | The voice to use for speech generation. Custom values are available |
| similarity | number | No | 1 | 0.00 ~ 1.00 | High enhancement boosts overall voice clarity and target speaker similarity. Very high values can cause artifacts, so adjusting this setting to find the optimal value is encouraged. |
| stability | number | No | 0.5 | 0.00 ~ 1.00 | Voice stability (0-1) Default value: 0.5 |
| use_speaker_boost | boolean | No | true | - | This parameter supports English text normalization, which improves performance in number-reading scenarios. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |