Voice creation: Difference between revisions
Created page with " Voice creation {{Drafting}} == List of voice creation == [https://elevenlabs.io/app/create-voice Voice Creation | ElevenLabs] {{access | date = 2026-11-01}} # Audio requirements: A minimum of 10 seconds; 30 seconds recommended. "Clone your voice with only 10 seconds of audio." # Pricing: Plan-based pricing with pay-as-you-go usage charges. The Starter plan costs $6 per month, with the first month priced at $1. # Key feature: Key feature: Automatically translate and..." |
mNo edit summary |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 8: | Line 8: | ||
[https://elevenlabs.io/app/create-voice Voice Creation | ElevenLabs] {{access | date = 2026-11-01}} | [https://elevenlabs.io/app/create-voice Voice Creation | ElevenLabs] {{access | date = 2026-11-01}} | ||
# Audio requirements: | # Developer / Company (country): ElevenLabs / Eleven Labs Inc. (United States; European headquarters in the United Kingdom).<ref>[https://elevenlabs.io/contact-legal ElevenLabs legal contact]</ref><ref>[https://elevenlabs.io/blog/london-office-opening ElevenLabs opens European HQ in London]</ref> | ||
# Audio requirements: At least 10 seconds total; 1–2 minutes recommended. Input languages follow Flash v2.5 and Multilingual v2 support.<ref>[https://elevenlabs.io/docs/eleven-creative/voices/voice-cloning/instant-voice-cloning Instant Voice Cloning]</ref><ref>[https://elevenlabs.io/docs/help-center/product/voices/voice-cloning/can-i-clone-my-voice-in-a-language-other-than-english Voice cloning languages]</ref> | |||
# | # Pricing: Starter: US$6/month; promotional first month: US$1.<ref>[https://elevenlabs.io/pricing ElevenLabs pricing]</ref> | ||
# Commercial use: Paid-plan outputs only, excluding Beta Services; rights remain after cancellation. Voice and content rights are required.<ref>[https://elevenlabs.io/docs/help-center/legal/can-i-publish-the-content-i-generate-on-the-platform Commercial use policy]</ref> | |||
# Key feature: Voice cloning and multilingual speech generation.<ref>[https://elevenlabs.io/docs/overview/capabilities/dubbing Dubbing | ElevenLabs Documentation]</ref> | |||
[https://huggingface.co/fishaudio/drama-3 Fish Audio Drama 3 | Hugging Face] {{access | date = 2026-11-01}} | |||
# Developer / Company (country): Fish Audio / 39 AI, Inc. (United States).<ref name="drama3-license">[https://huggingface.co/fishaudio/drama-3/blob/main/LICENSE Fish Audio Community License]</ref><ref>[https://www.linkedin.com/company/fish-audio Fish Audio company profile]</ref> | |||
# Audio requirements: Reference audio with a transcript; a 3.9-second example is provided, but no minimum is specified. The model lists 83 languages; input-language limits are unspecified.<ref name="drama3">[https://huggingface.co/fishaudio/drama-3 Drama 3 model card]</ref> | |||
# Pricing: Free model download; self-hosting costs apply. | |||
# Commercial use: Generally royalty-free below US$500,000 in combined annual revenue with affiliates. Hosted voice-generation services require a separate license; attribution and voice rights are required.<ref name="drama3-license" /> | |||
# Key feature: Voice cloning, emotion control, and streaming dialogue with up to 16 speakers.<ref name="drama3" /> | |||
== Related pages == | |||
* [[Taiwanese Mandarin Text-to-Speech Services]] | |||
== References == | == References == | ||
Latest revision as of 21:25, 1 November 2026
Voice creation
 This article "Voice creation" is still being written. If there are any incomplete parts, you are welcome to directly edit them. 這篇文章「Voice creation」內容還在撰寫中，如果有不完整的部分，歡迎你直接動手修改。
|
List of voice creation[edit]
Voice Creation | ElevenLabs [Last visited: 2026-11-01]
- Developer / Company (country): ElevenLabs / Eleven Labs Inc. (United States; European headquarters in the United Kingdom).[1][2]
- Audio requirements: At least 10 seconds total; 1–2 minutes recommended. Input languages follow Flash v2.5 and Multilingual v2 support.[3][4]
- Pricing: Starter: US$6/month; promotional first month: US$1.[5]
- Commercial use: Paid-plan outputs only, excluding Beta Services; rights remain after cancellation. Voice and content rights are required.[6]
- Key feature: Voice cloning and multilingual speech generation.[7]
Fish Audio Drama 3 | Hugging Face [Last visited: 2026-11-01]
- Developer / Company (country): Fish Audio / 39 AI, Inc. (United States).[8][9]
- Audio requirements: Reference audio with a transcript; a 3.9-second example is provided, but no minimum is specified. The model lists 83 languages; input-language limits are unspecified.[10]
- Pricing: Free model download; self-hosting costs apply.
- Commercial use: Generally royalty-free below US$500,000 in combined annual revenue with affiliates. Hosted voice-generation services require a separate license; attribution and voice rights are required.[8]
- Key feature: Voice cloning, emotion control, and streaming dialogue with up to 16 speakers.[10]