ElevenLabs Turbo v2.5
ElevenLabs Turbo v2.5 is a previous hosted TTS snapshot, not the live models default. The same page still lists leftover Turbo v2.5 and marks it deprecated.
Compare tts-1 if you wanted OpenAI's still-listed $15 / 1M-character leftover, and tts-1-hd if you wanted the higher-priced twin rather than this deprecated ElevenLabs SKU.
Key Features
- Previous Turbo SKU: older copy treated Turbo v2.5 as the current voice default. Confirm the models page before you hard-code it.
- Not the 2026 voice lead: Live models lead with Eleven v3 and Flash v2.5. Turbo v2.5 is deprecated on that page.
- No invented clone/language crown: Do not keep "most realistic / 1-minute clone / 29 languages as 2026 default" unless you re-verify a first-party card.
- Seat table is live, character table is not: Confirm elevenlabs.io/pricing for current seats. Do not paste leftover 10k / 30k / 100k / 500k character quotas.
Use Cases
- People with a Turbo v2.5 bookmark who need the catalog corrected.
- People who were about to paste Creator $22 and a 2024 character table into a 2026 deck.
Limitation: We did not synthesize a sample or time first-audio latency.
Pricing
elevenlabs.io/pricing on 2026-08-17.
| Piece | Price | Notes from that page |
|---|---|---|
| Free | $0 | Live free seat. |
| Starter | $6 / month | Live page. First month $3. Not leftover $5. |
| Creator | $22 / month | Live page. First month $11. Confirm credits on that page. |
| Pro | $99 / month | Live page. First month $49. |
| Scale / Business | Confirm pricing | Higher seats sit below Pro. Confirm the live official page. |
| Turbo v2.5 | Deprecated model | Still listed on the models page, not the 2026 default. |
If a leftover blog still calls Turbo v2.5 the current ElevenLabs default, treat v3 / Flash v2.5 as the correction.
Getting Started
- Open the models page before you hard-code Turbo v2.5.
- Confirm Eleven v3 or Flash v2.5 if you wanted the live hosted path.
- Confirm elevenlabs.io/pricing before you invent a character quota.
- Confirm tts-1 if you wanted a still-listed OpenAI leftover instead.
Frequently Asked Questions
Is Turbo v2.5 still the ElevenLabs default?
No.
Is Creator still $22 with 100k characters?
The live seat on the public page is $22 / month (first month $11). Do not keep the leftover 100k-character table unless you re-verify it on that page.
Same as OpenAI tts-1?
No. tts-1 is a still-listed OpenAI leftover at $15 / 1M characters. This slug is a deprecated ElevenLabs model.
Alternatives
- tts-1: Still-listed OpenAI TTS leftover, $15 / 1M characters.
- tts-1-hd: Still-listed higher-priced OpenAI twin.
- GPT-5.6 Sol: Live OpenAI frontier chat if you wandered here for a current model.
Tips
- Call Turbo v2.5 a deprecated leftover, not the current default voice.
- Point new ElevenLabs voice work at v3 or Flash v2.5.
- Keep only the live seat prices you confirmed; drop the leftover character table.
Conclusion
ElevenLabs Turbo v2.5 is a deprecated leftover still on the models page, not the 2026 ElevenLabs voice default. Start at elevenlabs.io/docs/overview/models, then decide whether v3 or Flash v2.5 already covers the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
DeepSeek V2.5
www.deepseek.com
Previous DeepSeek V2.5 snapshot. Not a 2026 chat+coder default.
Google: Gemini 3.1 Flash TTS
ai.google.dev/gemini-api/docs/models
Google Gemini 3.1 Flash TTS: leftover TTS sibling on the live Gemini models page. Not the 2026 Flash default.
Claude 3.5 Sonnet
docs.claude.com/en/docs/about-claude/models/overview
Previous Claude 3.5 Sonnet snapshot. Not the 2026 default.
Related Insights

Grok Bot and Hermes Bot: one person finally gets a think tank and a secretariat
Grok Bot now ships with Cursor Pro+. Hermes Bot runs on a VPS. They are not smarter chat boxes. The think tank advises, the secretariat executes, and you still make the call.
Hook OpenCode Go into Codex on Windows. Do Not Open a Second Toolkit.
A ChatGPT-signed Codex desktop app still shows mostly GPT in the picker. On Windows, enable only OpenCode Go and the Grok, GLM, Kimi, DeepSeek, and MiniMax models you already pay for appear in the same selector. Keys stay local. Native GPT stays put.
What Locks Codex Is the Picker, Not the Models
You already pay for OpenCode Go, Grok, and Z.ai, but the Codex picker still shows mostly GPT. The community project codex-router does not teach another install ritual. It puts subscriptions you already bought back into the selector, keeps keys on the machine, and leaves native GPT alone.