<!-- GENERATED BY scripts/gen_model_pages.py; speech hub; do not edit directly -->
# Chinese Speech API for ASR and TTS

> Data-driven directory of 12 speech recognition and text-to-speech models available through ChinaAPI.

- Canonical page: https://chinaapi-ru.com/speech-api/
- Catalog updated: 2026-07-13
- Data source: `scripts/models-data.json`; audio prices are reconciled with the ChinaAPI gateway
- Access: one ChinaAPI key; no mainland-China account or phone number required
- Sign up: https://dash.chinaapi-ru.com/register?utm_source=chinaapi&utm_medium=speech-md&utm_campaign=speech-api

## Available models

| Model ID | Workload | Endpoint | Request mode | Billing | Model page |
|---|---|---|---|---|---|
| mimo-v2.5-asr | Speech recognition (ASR) | POST https://api.chinaapi-ru.com/v1/chat/completions | Chat Completions with an input_audio payload | $0.0694 per audio hour | [details](https://chinaapi-ru.com/models/mimo-v2.5-asr/) |
| mimo-v2.5-tts | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/chat/completions | Chat Completions with messages plus an audio output configuration | $0 per 10k characters Limited-time free upstream pricing; check live pricing before production rollout. | [details](https://chinaapi-ru.com/models/mimo-v2.5-tts/) |
| stepaudio-2.5-tts | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.8056 per 10k characters | [details](https://chinaapi-ru.com/models/stepaudio-2.5-tts/) |
| glm-asr-2512 | Speech recognition (ASR) | POST https://api.chinaapi-ru.com/v1/audio/transcriptions | OpenAI-compatible transcription endpoint | $0.5 per audio hour | [details](https://chinaapi-ru.com/models/glm-asr-2512/) |
| glm-tts | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.5556 per 10k characters | [details](https://chinaapi-ru.com/models/glm-tts/) |
| qwen3-asr-flash | Speech recognition (ASR) | POST https://api.chinaapi-ru.com/v1/audio/transcriptions | OpenAI-compatible transcription endpoint | $0.11 per audio hour | [details](https://chinaapi-ru.com/models/qwen3-asr-flash/) |
| qwen3-tts-flash | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.1111 per 10k characters | [details](https://chinaapi-ru.com/models/qwen3-tts-flash/) |
| speech-2.8-hd | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.4861 per 10k characters | [details](https://chinaapi-ru.com/models/speech-2.8-hd/) |
| speech-2.8-turbo | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.2778 per 10k characters | [details](https://chinaapi-ru.com/models/speech-2.8-turbo/) |
| step-tts-2 | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.3889 per 10k characters | [details](https://chinaapi-ru.com/models/step-tts-2/) |
| step-tts-mini | Text to speech (TTS) | POST https://api.chinaapi-ru.com/v1/audio/speech | OpenAI-compatible speech endpoint | $0.125 per 10k characters | [details](https://chinaapi-ru.com/models/step-tts-mini/) |
| stepaudio-2.5-asr | Speech recognition (ASR) | POST https://api.chinaapi-ru.com/v1/audio/transcriptions | OpenAI-compatible transcription endpoint | $0.0208 per audio hour | [details](https://chinaapi-ru.com/models/stepaudio-2.5-asr/) |

## Compatibility boundary

OpenAI-compatible does not mean that every model uses one universal audio route. stepaudio-2.5-tts, glm-tts, qwen3-tts-flash, speech-2.8-hd, speech-2.8-turbo, step-tts-2, step-tts-mini uses /v1/audio/speech. glm-asr-2512, qwen3-asr-flash, stepaudio-2.5-asr use /v1/audio/transcriptions. mimo-v2.5-asr, mimo-v2.5-tts use /v1/chat/completions with model-specific audio payloads. Clients must send the payload required by the selected model.

## Quickstarts

### mimo-v2.5-asr

```sh
AUDIO_BASE64=$(base64 < meeting.wav | tr -d '\n')

curl -X POST https://api.chinaapi-ru.com/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2.5-asr",
    "messages": [{
      "role": "user",
      "content": [{
        "type": "input_audio",
        "input_audio": {"data": "data:audio/wav;base64,'"$AUDIO_BASE64"'"}
      }]
    }]
  }'
```

### mimo-v2.5-tts

```sh
curl -X POST https://api.chinaapi-ru.com/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2.5-tts",
    "messages": [
      {"role": "user", "content": "Natural, clear, and friendly delivery"},
      {"role": "assistant", "content": "Welcome to ChinaAPI. 欢迎使用语音模型。"}
    ],
    "audio": {"format": "wav", "voice": "冰糖"}
  }' > response.json
```

### stepaudio-2.5-tts

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepaudio-2.5-tts",
    "voice": "cixingnansheng",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### glm-asr-2512

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-..." \
  -F "model=glm-asr-2512" \
  -F "file=@meeting.wav" \
  -F "response_format=json"
```

### glm-tts

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-tts",
    "voice": "tongtong",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### qwen3-asr-flash

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-..." \
  -F "model=qwen3-asr-flash" \
  -F "file=@meeting.wav" \
  -F "response_format=json"
```

### qwen3-tts-flash

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-tts-flash",
    "voice": "Cherry",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### speech-2.8-hd

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "speech-2.8-hd",
    "voice": "Chinese (Mandarin)_Warm_Bestie",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### speech-2.8-turbo

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "speech-2.8-turbo",
    "voice": "Chinese (Mandarin)_Warm_Bestie",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### step-tts-2

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "step-tts-2",
    "voice": "cixingnansheng",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### step-tts-mini

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/speech \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "step-tts-mini",
    "voice": "cixingnansheng",
    "input": "（轻声）Welcome to ChinaAPI. 今天我们来测试自然语音。",
    "response_format": "mp3"
  }' \
  --output speech.mp3
```

### stepaudio-2.5-asr

```sh
curl -X POST https://api.chinaapi-ru.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-..." \
  -F "model=stepaudio-2.5-asr" \
  -F "file=@meeting.wav" \
  -F "response_format=json"
```

## Use cases

- **mimo-v2.5-asr — Transcription and audio understanding:** Xiaomi MiMo-V2.5-ASR — speech recognition for Chinese, English, code-switching, regional dialects, noisy recordings, far-field audio, multiple speakers, and lyrics.
- **mimo-v2.5-tts — Controllable voice output:** Xiaomi MiMo-V2.5-TTS — expressive multilingual speech synthesis with built-in voices, natural-language style instructions, emotion, pace, tone, dialect, and character control.
- **stepaudio-2.5-tts — Speech output through a dedicated route:** StepAudio 2.5 TTS — contextual speech synthesis with inline natural-language direction, expressive delivery, built-in voices, and OpenAI-compatible audio output.
- **glm-asr-2512 — Transcription and audio understanding:** GLM-ASR-2512 — multilingual streaming speech recognition for meetings, support calls, subtitles, and noisy recordings, with hotword support and Chinese dialect coverage.
- **glm-tts — Speech output through a dedicated route:** GLM-TTS — context-aware speech synthesis with expressive delivery, streaming output, fast first audio, and controls for voice, speed, and volume.
- **qwen3-asr-flash — Transcription and audio understanding:** Qwen3-ASR-Flash — multilingual file transcription with language hints, inverse text normalization, emotion recognition, and OpenAI-compatible audio input.
- **qwen3-tts-flash — Speech output through a dedicated route:** Qwen3-TTS-Flash — low-latency multilingual speech synthesis with mixed-language input, built-in voices, automatic language matching, and character-based billing.
- **speech-2.8-hd — Speech output through a dedicated route:** MiniMax Speech 2.8 HD — high-fidelity speech synthesis with natural emotional delivery, language enhancement, voice controls, and production audio formats.
- **speech-2.8-turbo — Speech output through a dedicated route:** MiniMax Speech 2.8 Turbo — speed-focused speech synthesis with natural output, emotion controls, language enhancement, and common production audio formats.
- **step-tts-2 — Speech output through a dedicated route:** Step TTS 2 — expressive speech synthesis with official and cloned voices, speed and volume control, pronunciation mapping, and multiple output formats.
- **step-tts-mini — Speech output through a dedicated route:** Step TTS Mini — cost-efficient expressive speech synthesis for Chinese, English, Japanese, Cantonese, and Sichuanese, with official and cloned voices.
- **stepaudio-2.5-asr — Transcription and audio understanding:** StepAudio 2.5 ASR — a 4B MTP streaming transcription model for fast Chinese-English recognition, ITN normalization, subtitles, meetings, and voice agents.

## Pricing note

Prices and billing units above are generated from the same catalog used for the model pages. The displayed media rate may include a service margin covering provider input/output billing, payment processing, chargeback exposure, and operations. Any margin is included in the displayed rate and is not added separately. Check the live pricing page before a production rollout: https://dash.chinaapi-ru.com/pricing?utm_source=chinaapi&utm_medium=speech-md&utm_campaign=speech-api

---
Markdown twin of https://chinaapi-ru.com/speech-api/ — generated by scripts/gen_model_pages.py. Full catalog: https://chinaapi-ru.com/llms-full.txt