---
title: "List available voices"
method: GET
path: "/voices"
tags: ["Voices"]
---

# List available voices

`GET /voices`

Returns all available AI voices for video narration, sorted by popularity. Use the voice `id` as the `voiceId` parameter when generating a video.

**No authentication required.** This is a public endpoint.

**Multilingual support:** All voices are multilingual and work across any language. Set the `language` parameter when generating a video and the voice will speak naturally in that language. The `optimizedFor` field lists languages where the voice has been specifically fine-tuned for best pronunciation and natural delivery.

**Filtering:** Use query parameters to narrow down voices by gender, accent, age, or use case. Combine multiple filters to find the perfect voice.

**For full details and interactive testing, refer to the [API documentation](https://app.aituber.app/api-docs).**

## Query parameters

- `gender` string — Filter by voice gender. Values: "male", "female", "neutral".
- `accent` string — Filter by accent (case-insensitive). Examples: "American", "British", "Australian", "Indian".
- `age` string — Filter by age group. Values: "young", "middle_aged", "old".
- `useCase` string — Filter by recommended use case (case-insensitive). Examples: "narration", "conversational", "news", "audiobook", "social_media".
- `language` string — Filter to voices optimized for a specific language (ISO 639-1 code). Examples: "en", "es", "fr", "hi", "zh".
- `search` string — Search voices by name or description (case-insensitive). Examples: "roger", "energetic", "calm".

## Response `200`

OK

- object[] — List of voices sorted by popularity (most popular first).
  - `id` string, required — Unique voice identifier. Pass this as the `voiceId` parameter when generating a video.
  - `name` string, required — Voice name (e.g. "Roger", "Sarah", "James").
  - `description` string, required — Voice characteristics and style (e.g. "Laid-Back, Casual, Resonant").
  - `previewUrl` string, uri, required — Audio preview URL (MP3). Play this to hear how the voice sounds before selecting it.
  - `gender` string, nullable, required — Voice gender (e.g. "male", "female", "neutral").
  - `age` string, nullable, required — Approximate age group (e.g. "young", "middle_aged", "old").
  - `accent` string, nullable, required — Primary accent (e.g. "American", "British", "Australian", "Indian"). Not all voices have an accent label.
  - `useCase` string, nullable, required — Recommended use case (e.g. "narration", "conversational", "news", "audiobook", "social_media"). This is a suggestion; any voice works for any use case.
  - `optimizedFor` string[], required — ISO 639-1 language codes where this voice has been specifically fine-tuned for best pronunciation and natural delivery (e.g. ["en", "fr", "es"]).

---

[API](https://skmtc.net/aituber/apis/aituber-api.md) · [All operations](https://skmtc.net/aituber/apis/aituber-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aituber/aituber-api/revisions/35448566f143/schema)