# Fish Audio Drama 3 vs Ming-3.0-tts-tiny

> Fish Audio Drama 3 scores 55.6 (C) to Ming-3.0-tts-tiny's 52.2 (D) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny
- Markdown: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-23

Fish Audio Drama 3 scores 55.6 (C) on agent readiness against Ming-3.0-tts-tiny's 52.2 (D), and leads in 3 of 4 scored categories. Ming-3.0-tts-tiny leads on risk. Both do text-to-speech.

- Fish Audio Drama 3: grade C, 55.6/100, rank #82 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/fish-audio-drama-3.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-drama-3.json
- Ming-3.0-tts-tiny: grade D, 52.2/100, rank #93 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/ming-3-0-tts-tiny.md · JSON https://www.anchorterminal.com/api/v1/tools/ming-3-0-tts-tiny.json
- Best text-to-speech APIs for AI agents: https://www.anchorterminal.com/best/text-to-speech/index.md
- All 87 tts comparisons: https://www.anchorterminal.com/compare/text-to-speech/index.md
- Best voice cloning and custom voice APIs for AI agents: https://www.anchorterminal.com/best/voice-cloning/index.md
- All 87 cloning comparisons: https://www.anchorterminal.com/compare/voice-cloning/index.md

## Which one, for what

### Fish Audio Drama 3 (C)

Good for: Agents with an NVIDIA GPU of 32 GB or more producing directed multi-character audio, dubbing or narration, for organisations under USD 500,000 revenue or non-commercial use

Ahead on:
- Reach, 60 against 50
- Agent interface, 70 against 60
- Documentation and upkeep, 51 against 44

Watch for: Commercial use is free only below USD 500,000 annual revenue, hosted services always need a separate licence, and the grant is revocable

### Ming-3.0-tts-tiny (D)

Good for: Agents on a 24 GB NVIDIA GPU that need Chinese or English narration, voice cloning or multi-speaker audio under MIT

Ahead on:
- Risk, 55 against 25

Watch for: No runtime among llama.cpp, Ollama, vLLM, SGLang, LM Studio or Transformers runs it from its own code


## Score by category

| Category | Weight | Fish Audio Drama 3 | Ming-3.0-tts-tiny | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 60 | 50 | Fish Audio Drama 3 +10 |
| Risk | 20% (20 this run) | 25 | 55 | Ming-3.0-tts-tiny +30 |
| Agent interface | 10% (10 this run) | 70 | 60 | Fish Audio Drama 3 +10 |
| Documentation and upkeep | 10% (10 this run) | 51 | 44 | Fish Audio Drama 3 +7 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **55.6 · C** | **52.2 · D** | |

## Facts side by side

| Fact | Fish Audio Drama 3 | Ming-3.0-tts-tiny |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Fish Audio | inclusionAI (Ant Group) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Fish Audio Community License 1.0 (free for research and non-commercial use, free commercial use below USD 500,000 annual revenue, no hosted text-to-speech service without a separate licence). The card's metadata still names fish-audio-research-license | MIT |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-17 | 2026-10-20 |
| Terms last updated |  | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 2.8/5 (4) | 2.5/5 (4) |

## Verdicts

**Fish Audio Drama 3.** A local voice cousin for directed speech, multi-character scenes, voice cloning and word-level edits in about 80 languages. It needs an NVIDIA GPU, about 29 GB for the int4 build or at least 48 GB for FP8, through SGLang-Omni or fish-speech. The main risk is the licence, revocable, capped at USD 500,000 revenue for commercial use and barring hosted services.

**Ming-3.0-tts-tiny.** A text-to-speech cousin for voice cloning, voice design and multi-speaker podcast audio in seven languages, under MIT. It needs the publisher's own code or SGLang-Omni and about 22 GB of GPU memory, with CUDA 11.8 pinned. The main risks are that loading runs repository code, no safety work is published and it can clone a voice from a short clip.

## Before you call either

### Fish Audio Drama 3

1. Install SGLang-Omni from source with `uv pip install --prerelease=allow -e ".[fishaudio]"`, then `sgl-omni serve --model-path fishaudio/drama-3-int4 --port 8000` (or fishaudio/drama-3 for FP8 on 48 GB or more)
2. POST JSON to /v1/audio/speech with `input`, optional `references` (audio_path and its transcript) and `previous_takes`; set `response_format` and `stream` for the output
3. Start each line with `<|speaker:N|>` (N from 0 to 15) for several voices, and separate lines with `<|audio_separator|>`
4. Direct with point tags like `[sighs]`, scoped tags like `<whisper>...</whisper>`, a bracketed style prefix, or `Direction:` and `Line:` for a director's note
5. The int4 build needs compute capability 8.0 or newer; only the triton attention backend is accepted
6. Keep each reference clip under 60 seconds and the prompt under 8,192 rows, about 21.5 rows per second of reference audio
7. Check the licence before commercial use or exposing it to other users, and only clone voices with consent
8. Treat text from untrusted sources as a script that can carry directions and speaker tags

### Ming-3.0-tts-tiny

1. Install from the GitHub repository, `git clone https://github.com/inclusionAI/Ming-3.0-tts.git && cd Ming-3.0-tts && pip install -r requirements-tiny.txt`, in its own Python 3.10.15 environment, since the 0.5B model pins different versions
2. Quick start is `bash examples/one_click/run_seed.sh`, which clones from the bundled reference clip
3. To serve, run `sgl-omni serve --model-path inclusionAI/Ming-3.0-tts-tiny` from SGLang-Omni's main branch and POST to /v1/audio/speech with input, response_format and, for cloning, ref_audio plus ref_text
4. Pick one task per call (seed, multilingual, paralinguistic, podcast, basic, emotion, dialect, freeform, voice_design, ip) and pass only the inputs that task accepts
5. Expect one complete audio body, since there is no streaming, and no timestamps
6. Pass temperature yourself, since the reference generate() uses 0 and SGLang-Omni takes 1.5 from the config
7. Run `python tools/preflight_tiny.py --model_path <dir>` on the downloaded checkpoint before first use
8. Label output as synthetic speech where it could pass for a real recording, as the card asks

## Questions

### Which is better for AI agents, Fish Audio Drama 3 or Ming-3.0-tts-tiny?

Fish Audio Drama 3 scores 55.6 (C) on agent readiness against Ming-3.0-tts-tiny's 52.2 (D), and leads in 3 of 4 scored categories. Ming-3.0-tts-tiny leads on risk.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-tiny.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "fish-audio-drama-3", "b": "ming-3-0-tts-tiny"}`. From a terminal: `anchor compare fish-audio-drama-3 ming-3-0-tts-tiny`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fish-audio-drama-3.json and https://www.anchorterminal.com/api/v1/tools/ming-3-0-tts-tiny.json

## Other comparisons with Fish Audio Drama 3 or Ming-3.0-tts-tiny

- [Fish Audio Drama 3 vs Fish Audio S2 Pro](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-fish-audio-s2-pro.md)
- [Fish Audio Drama 3 vs Ming-3.0-tts-0.5B](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-ming-3-0-tts-0-5b.md)
- [Fish Audio Drama 3 vs OmniVoice](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-omnivoice.md)
- [Fish Audio Drama 3 vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-qwen3-tts-1-7b-customvoice.md)
- [Fish Audio Drama 3 vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-vieneu-tts-v3-turbo.md)
- [Fish Audio S2 Pro vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-ming-3-0-tts-tiny.md)
- [Ming-3.0-tts-0.5B vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-ming-3-0-tts-tiny.md)
- [Ming-3.0-tts-tiny vs OmniVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-omnivoice.md)
- [Ming-3.0-tts-tiny vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-qwen3-tts-1-7b-customvoice.md)
- [Ming-3.0-tts-tiny vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-vieneu-tts-v3-turbo.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp