Markdown edition

# Runway's Eleven v4 speech API: request shape and October pricing

> Runway's Eleven v4 speech API accepts scripts up to 2,500 characters. This documentation-based guide explains the request, task result, account setup and October 12 price change.

By BIG CHANGE Editorial

Published: 2026-10-06T06:30:01.909Z
Updated: 2026-10-06T06:30:01.909Z
Canonical: https://bigchange.ai/blog/runway-eleven-v4-text-to-speech-api-price-change

![Conceptual charcoal illustration of unbranded headphones resting beside a loose script sheet with abstract text strokes.](https://bigchange.ai/api/media/file/runway-eleven-script-audio-hero-v1.png)
AI-generated conceptual illustration by BIG CHANGE. A written script and headphones represent text-to-speech; no API test or audio assessment is depicted.

Runway added Eleven v4 to its developer API on September 30. Its [release note](https://docs.dev.runwayml.com/api-details/api_changelog/) identifies the model as `eleven_v4`, caps a script at 2,500 characters and says the credit rate will rise on October 12, 2026 Pacific Time. For developers adding speech generation to a production workflow, the useful question is what a valid request needs and how much the documented rate means in dollars. This guide is based on Runway's documentation checked October 6; BIG CHANGE did not make a paid API call or assess the audio.

## The big change

- **What changed:** Runway now lists Eleven v4 as a text-to-speech model behind its existing task API. A script can include documented audio tags such as `[laughs]`, `[whispers]` and `[pause]`, within the 2,500-character limit.
- **Why it matters:** A team with a Runway developer project can request speech using a preset voice and retrieve the completed task's audio URL. Its integration and budget planning can use one documented request shape and a dated price schedule.
- **What to watch:** Runway says the rate changes from 2.2 to 5 credits per 1,000 characters on October 12, 2026 PT. Anyone estimating repeated generations needs to use the rate effective when the request is billed and check the live price before committing a budget.

## Set up a project and key

Runway's [setup guide](https://docs.dev.runwayml.com/guides/setup/) says to create an account and project in the developer portal, then create a project API key under API Keys. Creating or disabling a key requires an Admin or Developer role. The key appears in plaintext once, so store it securely. For SDK use, Runway says to set `RUNWAYML_API_SECRET`; its SDK reads that variable automatically. Keep the secret out of source code.

The project also needs credits before it can use the API. Runway says the minimum initial payment is **$10**, at **$0.01 per credit**, through the project's billing tab. An Admin or Billing admin role is needed to add credits. That is a minimum credit purchase, not the charge for one speech request. The setup page does not describe a free first call.

## Send a text-to-speech request

The [Runway Python SDK's current request type](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/types/text_to_speech_create_params.py) requires `model`, `prompt_text` and a `voice` object for Eleven v4. On the wire, the corresponding JSON fields are `model`, `promptText` and `voice`, with `voice.type` set to `runway-preset` and a `presetId`. `Bernard` is one listed preset. The [SDK service](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/resources/text_to_speech.py) posts this request to `/v1/text_to_speech` and returns a new task response. Runway's [API guide](https://docs.dev.runwayml.com/guides/using-the-api/) documents the host, bearer key and `X-Runway-Version: 2024-11-06` header used for direct HTTP calls.

This is a documentation-derived request body, not a call we ran:

```json
{
  "model": "eleven_v4",
  "promptText": "The recording begins now. [pause] Welcome.",
  "voice": {
    "type": "runway-preset",
    "presetId": "Bernard"
  }
}
```

Runway's September 30 [changelog entry](https://docs.dev.runwayml.com/api-details/api_changelog/) names `[laughs]`, `[whispers]` and `[pause]` as supported examples and says Eleven v4 uses the same Runway preset voices as Eleven v3. Tags are part of the script; leave room for them within the stated 2,500-character maximum. The SDK also lists optional voice settings, language and neighboring text fields. Its schema does not establish that any setting guarantees a particular delivery, and this article makes no claim about voice quality or latency.

The initial response is a task, rather than audio bytes. Runway's [output guide](https://docs.dev.runwayml.com/assets/outputs/) says to query `GET /v1/tasks/:id`; a succeeded task contains an `output` array of result URLs. Those URLs expire within 24–48 hours of accessing the API, so download the result into your own storage rather than using the temporary URL in a product. The general output example is a video task; it establishes the task response shape, while the [models list](https://docs.dev.runwayml.com/guides/models/) identifies Eleven v4's output as audio. We have not observed an Eleven v4 response or verified its audio file format.

## Calculate the dated price

Runway's [pricing page](https://docs.dev.runwayml.com/guides/pricing/) and release note list **2.2 credits per 1,000 characters until October 12, 2026 PT**, then **5 credits per 1,000 characters**, with a **one-credit minimum**. At the published $0.01 per credit, those rates translate to **$0.022** and **$0.05 per 1,000 characters** before any applicable tax. The later listed rate is about 2.27 times the earlier one.

For a transparent planning example, ten separate scripts of exactly 1,000 billable characters each would total 10,000 characters. Multiplying the published rates gives **22 credits, or $0.22**, at the earlier rate and **50 credits, or $0.50**, at the later rate. Each script is below the 2,500-character limit, and each calculated request is above the one-credit minimum. This is arithmetic from Runway's listed rates, not an observed invoice. The cited pages do not specify how billable characters treat tags or whether fractional per-request charges are rounded, so a production estimator should check actual usage records and current terms.

## Sources & further reading

Runway's [September 30 API changelog](https://docs.dev.runwayml.com/api-details/api_changelog/) establishes the release date, model ID, tag examples, script cap and dated pricing statement. The [setup guide](https://docs.dev.runwayml.com/guides/setup/) explains project, key and credit prerequisites, including role permissions and the initial $10 payment. The [pricing page](https://docs.dev.runwayml.com/guides/pricing/) supplies the credit-to-dollar conversion and listed Eleven v4 rates.

The [Python SDK request schema](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/types/text_to_speech_create_params.py) and [service implementation](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/resources/text_to_speech.py) establish the field names, preset voice shape, endpoint path and task creation response inspected for this guide. Runway's [getting started guide](https://docs.dev.runwayml.com/guides/using-the-api/), [model list](https://docs.dev.runwayml.com/guides/models/) and [output guide](https://docs.dev.runwayml.com/assets/outputs/) supply the HTTP version header, audio output classification and task retrieval behavior. These are provider documents, not an independent performance test. Checked October 6, 2026.

## Sources

- [Runway Dev API changelog: Eleven v4](https://docs.dev.runwayml.com/api-details/api_changelog/) — Runway's September 30 entry announces eleven_v4, the 2,500-character script cap, three audio tag examples, Runway preset voices, and the October 12 PT change from 2.2 to 5 credits per 1,000 characters with a one-credit minimum. It does not establish audio quality or a successful BIG CHANGE call.
- [Runway Dev API setup](https://docs.dev.runwayml.com/guides/setup/) — Documents account, project, API key and role prerequisites; SDK secret environment variable; and the $10 minimum initial credit purchase at $0.01 per credit. These are provider instructions, not steps this article tested.
- [Runway Dev API pricing](https://docs.dev.runwayml.com/guides/pricing/) — Lists Eleven v4's two dated credit rates and $0.01 per credit. The article's $0.22 and $0.50 example is arithmetic for ten 1,000-character requests, not an observed bill; sales tax may apply.
- [Runway Python SDK: text-to-speech request schema](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/types/text_to_speech_create_params.py) — Current official SDK main branch defines ElevenV4 required model, promptText alias and runway-preset voice with presetId; Bernard is listed. Main is mutable and the request was not executed.
- [Runway Python SDK: text-to-speech service](https://github.com/runwayml/sdk-python/blob/main/src/runwayml/resources/text_to_speech.py) — Current official SDK service posts to /v1/text_to_speech and returns a new-task response. It does not demonstrate an observed Eleven v4 response.
- [Runway Dev: using the API](https://docs.dev.runwayml.com/guides/using-the-api/) — Documents the API host, bearer key, X-Runway-Version 2024-11-06 header and task-ID pattern in generation examples. The examples inspected are not Eleven v4 calls.
- [Runway Dev: output formats](https://docs.dev.runwayml.com/assets/outputs/) — Describes GET /v1/tasks/:id, succeeded-task output URL arrays and 24–48 hour URL expiry. The displayed example is a video task, so no Eleven v4 audio format is inferred.
- [Runway Dev: available models](https://docs.dev.runwayml.com/guides/models/) — Lists eleven_v4 as text input and audio output. This is model classification, not independent audio inspection.